Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4694 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4035. Min Range: -6.4035
Max Act: 6.4035. Min Act: -0.1700
Data Index: 3038500 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.9660. Min Act: -0.1700
Data Index: 2962167 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.9660. Min Act: -0.1700
Data Index: 7783478 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.9660. Min Act: -0.1700
Data Index: 7020403 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.9347. Min Act: -0.1700
Data Index: 4704866 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.9347. Min Act: -0.1700
Data Index: 990190 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.9035. Min Act: -0.1700
Data Index: 4840212 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.8722. Min Act: -0.1700
Data Index: 854366 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.9035. Min Act: -0.1700
Data Index: 5750979 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.8722. Min Act: -0.1700
Data Index: 6779853 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.8722. Min Act: -0.1700
Data Index: 7415496 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.8410. Min Act: -0.1700
Data Index: 8459837 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.8097. Min Act: -0.1700
Data Index: 5960253 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.8097. Min Act: -0.1700
Data Index: 7107898 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6035030 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.8097. Min Act: -0.1700
Data Index: 3560282 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.7785. Min Act: -0.1700
Data Index: 983737 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.7785. Min Act: -0.1700
Data Index: 5984433 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.7785. Min Act: -0.1700
Data Index: 4111624 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4035. Min Range: -6.4035
Max Act: 5.7785. Min Act: -0.1700
Data Index: 1824490 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19