Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.2974. Min Act: -0.1700
Data Index: 2969725 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.2036. Min Act: -0.1700
Data Index: 401675 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.2036. Min Act: -0.1700
Data Index: 1445170 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.1411. Min Act: -0.1700
Data Index: 3640092 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.1411. Min Act: -0.1700
Data Index: 1276211 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.0786. Min Act: -0.1700
Data Index: 8696377 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.0474. Min Act: -0.1700
Data Index: 1518378 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9849. Min Act: -0.1700
Data Index: 1050514 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9849. Min Act: -0.1700
Data Index: 1419832 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9849. Min Act: -0.1700
Data Index: 5561083 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 3394304 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 718213 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 5785061 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 7655920 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 5033659 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 8033368 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.8911. Min Act: -0.1700
Data Index: 4717320 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.8911. Min Act: -0.1700
Data Index: 8696374 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 939038 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 3381433 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19