Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2733. Min Range: -10.2733
Max Act: 10.2733. Min Act: -0.1700
Data Index: 1539383 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2733. Min Range: -10.2733
Max Act: 9.3358. Min Act: -0.1700
Data Index: 5433232 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2733. Min Range: -10.2733
Max Act: 9.2733. Min Act: -0.1700
Data Index: 7085000 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2733. Min Range: -10.2733
Max Act: 9.1483. Min Act: -0.1700
Data Index: 7640624 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2733. Min Range: -10.2733
Max Act: 9.0233. Min Act: -0.1700
Data Index: 2680864 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.8358. Min Act: -0.1700
Data Index: 6022152 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.6483. Min Act: -0.1700
Data Index: 2523766 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.6483. Min Act: -0.1700
Data Index: 8220600 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.5233. Min Act: -0.1700
Data Index: 3375120 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.5858. Min Act: -0.1700
Data Index: 5010729 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.5858. Min Act: -0.1700
Data Index: 4827498 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.5233. Min Act: -0.1700
Data Index: 8216937 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.5233. Min Act: -0.1700
Data Index: 3396793 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.5233. Min Act: -0.1700
Data Index: 630945 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.3983. Min Act: -0.1700
Data Index: 3151807 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.2733. Min Act: -0.1700
Data Index: 6264838 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.3358. Min Act: -0.1700
Data Index: 4076007 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.3358. Min Act: -0.1700
Data Index: 7721539 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.3358. Min Act: -0.1700
Data Index: 3864534 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2733. Min Range: -10.2733
Max Act: 8.2733. Min Act: -0.1700
Data Index: 142342 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19