Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2746 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.7777. Min Act: -0.1700
Data Index: 1597971 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.7777. Min Act: -0.1700
Data Index: 4491287 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.7152. Min Act: -0.1700
Data Index: 8709465 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.7152. Min Act: -0.1700
Data Index: 8286787 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6527. Min Act: -0.1700
Data Index: 7750871 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6527. Min Act: -0.1700
Data Index: 592394 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6527. Min Act: -0.1700
Data Index: 8409009 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6527. Min Act: -0.1700
Data Index: 7367913 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6527. Min Act: -0.1700
Data Index: 6024412 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6527. Min Act: -0.1700
Data Index: 5353952 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6215. Min Act: -0.1700
Data Index: 6919594 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6215. Min Act: -0.1700
Data Index: 1167415 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6215. Min Act: -0.1700
Data Index: 8078117 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.6215. Min Act: -0.1700
Data Index: 184216 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.5902. Min Act: -0.1700
Data Index: 2044378 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.5902. Min Act: -0.1700
Data Index: 5742984 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.5902. Min Act: -0.1700
Data Index: 3436348 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.5902. Min Act: -0.1700
Data Index: 831278 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.5902. Min Act: -0.1700
Data Index: 4169690 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7777. Min Range: -6.7777
Max Act: 6.5902. Min Act: -0.1700
Data Index: 3341724 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19