Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2717 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1322. Min Range: -7.1322
Max Act: 7.1322. Min Act: -0.1700
Data Index: 5488064 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1322. Min Range: -7.1322
Max Act: 7.0697. Min Act: -0.1700
Data Index: 5505458 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1322. Min Range: -7.1322
Max Act: 7.0385. Min Act: -0.1700
Data Index: 4661545 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1322. Min Range: -7.1322
Max Act: 7.0385. Min Act: -0.1700
Data Index: 116765 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.8822. Min Act: -0.1700
Data Index: 8280815 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.8197. Min Act: -0.1700
Data Index: 6151738 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.8197. Min Act: -0.1700
Data Index: 4605395 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7885. Min Act: -0.1700
Data Index: 7250038 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7885. Min Act: -0.1700
Data Index: 6636836 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7885. Min Act: -0.1700
Data Index: 8476830 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7885. Min Act: -0.1700
Data Index: 3150435 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7572. Min Act: -0.1700
Data Index: 2247253 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7572. Min Act: -0.1700
Data Index: 6287241 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7260. Min Act: -0.1700
Data Index: 4404373 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7885. Min Act: -0.1700
Data Index: 4088366 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7572. Min Act: -0.1700
Data Index: 1796405 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7260. Min Act: -0.1700
Data Index: 992857 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7572. Min Act: -0.1700
Data Index: 6759281 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.6947. Min Act: -0.1700
Data Index: 8272506 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1322. Min Range: -7.1322
Max Act: 6.7260. Min Act: -0.1700
Data Index: 6974335 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19