Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.4147. Min Act: -0.1700
Data Index: 1195013 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.3834. Min Act: -0.1700
Data Index: 396944 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.2897. Min Act: -0.1700
Data Index: 8522454 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.2584. Min Act: -0.1700
Data Index: 3314974 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.2272. Min Act: -0.1700
Data Index: 6918739 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.1959. Min Act: -0.1700
Data Index: 9971 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.1647. Min Act: -0.1700
Data Index: 2172899 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.1334. Min Act: -0.1700
Data Index: 3721187 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.1022. Min Act: -0.1700
Data Index: 4584799 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0709. Min Act: -0.1700
Data Index: 4711108 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0709. Min Act: -0.1700
Data Index: 7636404 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0709. Min Act: -0.1700
Data Index: 7713795 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0709. Min Act: -0.1700
Data Index: 4647760 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0397. Min Act: -0.1700
Data Index: 8719785 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0084. Min Act: -0.1700
Data Index: 7635983 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0084. Min Act: -0.1700
Data Index: 4626863 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0084. Min Act: -0.1700
Data Index: 1226700 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0084. Min Act: -0.1700
Data Index: 5230206 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0084. Min Act: -0.1700
Data Index: 5279581 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4147. Min Range: -7.4147
Max Act: 7.0084. Min Act: -0.1700
Data Index: 3166659 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19