Python
from transformers import GPT2Tokenizer, GPT2LMHeadModel
from bertviz import head_view
# Load GPT-2 model and tokenizer
model = GPT2LMHeadModel.from_pretrained("gpt2", output_attentions=True)
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
# Input text
text = "The role of explainability in AI is crucial for ethical decision-making."
# Tokenize input
inputs = tokenizer(text, return_tensors="pt")
# Generate attentions
outputs = model(**inputs)
attentions = outputs.attentions  # List of attention weights from all layers
# Visualize attention
head_view(attentions, tokenizer, text)

Python 
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load GPT-Neo model
model_name = "EleutherAI/gpt-neo-2.7B"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Define a prompt for controlling output style
prompt = (
    "Write an inspiring conclusion to an academic paper: \n"
    "In conclusion, the field of Explainable AI has the potential to..."
)
# Tokenize and generate text
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(inputs["input_ids"], max_length=100)

# Decode and display output
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Python 
import shap
from transformers import pipeline
# Load a text generation pipeline
generator = pipeline("text-generation", model="gpt2")
# Define SHAP explainer
explainer = shap.Explainer(generator)
# Input text
prompt = "Explainable AI improves trust in automated systems by"
# Generate explanations
shap_values = explainer([prompt])
# Visualize explanations
shap.text_plot(shap_values)

Python 
from captum.attr import IntegratedGradients
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
# Load model and tokenizer
model_name = "textattack/bert-base-uncased-imdb"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Input text
text = "Explainable AI has transformed how developers interact with machine learning models."
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
# Compute Integrated Gradients
ig = IntegratedGradients(model)
attributions = ig.attribute(inputs['input_ids'], target=1)
# Visualize attributions
print("Integrated Gradients Attributions:", attributions)

Python 
import torch
from transformers import BertTokenizer, BertModel
# Load BERT model and tokenizer
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
model = BertModel.from_pretrained("bert-base-uncased", output_attentions=True)
# Input sentence
text = "Natural Language Generation depends heavily on transformer architectures."
inputs = tokenizer(text, return_tensors="pt")
# Forward pass with attention
outputs = model(**inputs)
attention_weights = outputs.attentions  # Attention weights for each layer
# Analyze specific layer
layer_3_attention = attention_weights[3].detach().numpy()
print("Attention weights from layer 3:", layer_3_attention)