Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4312 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3432. Min Range: -7.3432
Max Act: 7.3432. Min Act: -0.1700
Data Index: 1742383 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3432. Min Range: -7.3432
Max Act: 7.1869. Min Act: -0.1700
Data Index: 4917356 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3432. Min Range: -7.3432
Max Act: 7.1869. Min Act: -0.1700
Data Index: 3925137 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3432. Min Range: -7.3432
Max Act: 7.1244. Min Act: -0.1700
Data Index: 352905 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.9994. Min Act: -0.1700
Data Index: 309910 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.9369. Min Act: -0.1700
Data Index: 3828488 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.7807. Min Act: -0.1700
Data Index: 7856239 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.7182. Min Act: -0.1700
Data Index: 4137369 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.6869. Min Act: -0.1700
Data Index: 7621898 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.6557. Min Act: -0.1700
Data Index: 5047522 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.6869. Min Act: -0.1700
Data Index: 3239366 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.6557. Min Act: -0.1700
Data Index: 824413 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.5932. Min Act: -0.1700
Data Index: 1848472 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.5619. Min Act: -0.1700
Data Index: 7424674 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.4994. Min Act: -0.1700
Data Index: 8740225 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.4994. Min Act: -0.1700
Data Index: 8254030 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.4682. Min Act: -0.1700
Data Index: 3558558 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.4682. Min Act: -0.1700
Data Index: 870818 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.4369. Min Act: -0.1700
Data Index: 7950068 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3432. Min Range: -7.3432
Max Act: 6.4057. Min Act: -0.1700
Data Index: 6586385 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19