Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4921 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.8712. Min Act: -0.1700
Data Index: 6003836 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.7774. Min Act: -0.1700
Data Index: 7736269 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.5587. Min Act: -0.1700
Data Index: 2047724 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.4962. Min Act: -0.1700
Data Index: 399602 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.4649. Min Act: -0.1700
Data Index: 6751496 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.4024. Min Act: -0.1700
Data Index: 8615727 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.2149. Min Act: -0.1700
Data Index: 11227 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.2149. Min Act: -0.1700
Data Index: 1787454 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.1837. Min Act: -0.1700
Data Index: 2160409 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.1212. Min Act: -0.1700
Data Index: 6914575 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.1212. Min Act: -0.1700
Data Index: 8141771 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.1212. Min Act: -0.1700
Data Index: 1965900 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.0899. Min Act: -0.1700
Data Index: 5015671 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.0899. Min Act: -0.1700
Data Index: 1300329 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.0587. Min Act: -0.1700
Data Index: 7691761 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8712. Min Range: -7.8712
Max Act: 7.0587. Min Act: -0.1700
Data Index: 8053991 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8712. Min Range: -7.8712
Max Act: 6.9962. Min Act: -0.1700
Data Index: 6384719 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8712. Min Range: -7.8712
Max Act: 6.9962. Min Act: -0.1700
Data Index: 1647256 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8712. Min Range: -7.8712
Max Act: 6.9962. Min Act: -0.1700
Data Index: 7267116 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8712. Min Range: -7.8712
Max Act: 6.9962. Min Act: -0.1700
Data Index: 1738549 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19