Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.3925. Min Act: -0.1700
Data Index: 7184687 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.3613. Min Act: -0.1700
Data Index: 6244220 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.3300. Min Act: -0.1700
Data Index: 8629922 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.2050. Min Act: -0.1700
Data Index: 939318 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1738. Min Act: -0.1700
Data Index: 7174369 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1425. Min Act: -0.1700
Data Index: 4713108 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1425. Min Act: -0.1700
Data Index: 3514090 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1425. Min Act: -0.1700
Data Index: 4061070 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.0488. Min Act: -0.1700
Data Index: 206716 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.0800. Min Act: -0.1700
Data Index: 19126 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.0488. Min Act: -0.1700
Data Index: 1380942 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3925. Min Range: -6.3925
Max Act: 5.9863. Min Act: -0.1700
Data Index: 1769872 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3925. Min Range: -6.3925
Max Act: 5.9863. Min Act: -0.1700
Data Index: 6254990 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3925. Min Range: -6.3925
Max Act: 5.9550. Min Act: -0.1700
Data Index: 3587932 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3925. Min Range: -6.3925
Max Act: 5.9238. Min Act: -0.1700
Data Index: 7947413 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3925. Min Range: -6.3925
Max Act: 5.9550. Min Act: -0.1700
Data Index: 2506349 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3925. Min Range: -6.3925
Max Act: 5.9238. Min Act: -0.1700
Data Index: 2716812 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3925. Min Range: -6.3925
Max Act: 5.8925. Min Act: -0.1700
Data Index: 7630317 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3925. Min Range: -6.3925
Max Act: 5.8925. Min Act: -0.1700
Data Index: 1532819 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3925. Min Range: -6.3925
Max Act: 5.8925. Min Act: -0.1700
Data Index: 8127558 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19