Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5755 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.5417. Min Act: -0.1700
Data Index: 6925804 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.3542. Min Act: -0.1700
Data Index: 6800391 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.1667. Min Act: -0.1700
Data Index: 4202426 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.1667. Min Act: -0.1700
Data Index: 3991679 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.1667. Min Act: -0.1700
Data Index: 867190 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.1042. Min Act: -0.1700
Data Index: 1774168 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.1042. Min Act: -0.1700
Data Index: 8721283 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.1042. Min Act: -0.1700
Data Index: 7644560 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.1042. Min Act: -0.1700
Data Index: 5602409 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.0417. Min Act: -0.1700
Data Index: 88993 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5417. Min Range: -9.5417
Max Act: 9.0417. Min Act: -0.1700
Data Index: 2136432 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5417. Min Range: -9.5417
Max Act: 8.9792. Min Act: -0.1700
Data Index: 1316018 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5417. Min Range: -9.5417
Max Act: 8.9167. Min Act: -0.1700
Data Index: 7142491 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5417. Min Range: -9.5417
Max Act: 8.9792. Min Act: -0.1700
Data Index: 2319226 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5417. Min Range: -9.5417
Max Act: 8.9792. Min Act: -0.1700
Data Index: 877384 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5417. Min Range: -9.5417
Max Act: 8.9792. Min Act: -0.1700
Data Index: 3445510 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5417. Min Range: -9.5417
Max Act: 8.9167. Min Act: -0.1700
Data Index: 5679073 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5417. Min Range: -9.5417
Max Act: 8.9167. Min Act: -0.1700
Data Index: 8546273 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5417. Min Range: -9.5417
Max Act: 8.9167. Min Act: -0.1700
Data Index: 7129484 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5417. Min Range: -9.5417
Max Act: 8.9792. Min Act: -0.1700
Data Index: 7217015 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19