Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.7959. Min Act: -0.1700
Data Index: 2243202 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.6709. Min Act: -0.1700
Data Index: 3639421 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5772. Min Act: -0.1700
Data Index: 8741161 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5772. Min Act: -0.1700
Data Index: 3197905 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5772. Min Act: -0.1700
Data Index: 2886361 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5772. Min Act: -0.1700
Data Index: 6005216 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5772. Min Act: -0.1700
Data Index: 2358929 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5147. Min Act: -0.1700
Data Index: 1509000 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5147. Min Act: -0.1700
Data Index: 2886366 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5147. Min Act: -0.1700
Data Index: 412848 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.4834. Min Act: -0.1700
Data Index: 7328850 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.4834. Min Act: -0.1700
Data Index: 2886359 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5147. Min Act: -0.1700
Data Index: 8523193 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.5147. Min Act: -0.1700
Data Index: 3006424 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.4522. Min Act: -0.1698
Data Index: 4104888 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.4522. Min Act: -0.1700
Data Index: 7575888 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.4522. Min Act: -0.1700
Data Index: 4243739 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.4209. Min Act: -0.1700
Data Index: 2110787 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.4522. Min Act: -0.1700
Data Index: 5383482 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7959. Min Range: -7.7959
Max Act: 7.3897. Min Act: -0.1700
Data Index: 7384181 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19