Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 203 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.9792. Min Act: -0.1700
Data Index: 7873117 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.8229. Min Act: -0.1700
Data Index: 7761381 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.7604. Min Act: -0.1700
Data Index: 1555742 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.7604. Min Act: -0.1700
Data Index: 6014147 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.6354. Min Act: -0.1700
Data Index: 4694296 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.6354. Min Act: -0.1700
Data Index: 8389626 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.6354. Min Act: -0.1700
Data Index: 289841 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.5729. Min Act: -0.1700
Data Index: 561220 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.5417. Min Act: -0.1700
Data Index: 3100699 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.5417. Min Act: -0.1700
Data Index: 338551 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.4479. Min Act: -0.1700
Data Index: 4213901 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.3854. Min Act: -0.1700
Data Index: 3679914 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.3854. Min Act: -0.1700
Data Index: 3983723 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.3854. Min Act: -0.1700
Data Index: 2343094 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.3854. Min Act: -0.1700
Data Index: 6516193 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.3854. Min Act: -0.1700
Data Index: 184438 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.3854. Min Act: -0.1700
Data Index: 3679919 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.3854. Min Act: -0.1700
Data Index: 329028 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.3542. Min Act: -0.1700
Data Index: 5998106 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9792. Min Range: -5.9792
Max Act: 5.3854. Min Act: -0.1700
Data Index: 7449978 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19