Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 581 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1551. Min Range: -5.1551
Max Act: 5.1551. Min Act: -0.1700
Data Index: 1960503 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.9676. Min Act: -0.1700
Data Index: 902417 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.9676. Min Act: -0.1700
Data Index: 3368121 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.9676. Min Act: -0.1700
Data Index: 5243525 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.9676. Min Act: -0.1700
Data Index: 2483595 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.9363. Min Act: -0.1700
Data Index: 3411860 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.9363. Min Act: -0.1700
Data Index: 3707444 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.8738. Min Act: -0.1700
Data Index: 5564543 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.8113. Min Act: -0.1700
Data Index: 2346975 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.8426. Min Act: -0.1700
Data Index: 5957848 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.8426. Min Act: -0.1700
Data Index: 2930287 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.8426. Min Act: -0.1700
Data Index: 7326958 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.8113. Min Act: -0.1700
Data Index: 6488858 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.8113. Min Act: -0.1700
Data Index: 3430494 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.7488. Min Act: -0.1700
Data Index: 5389408 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.7801. Min Act: -0.1700
Data Index: 7422955 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.7176. Min Act: -0.1700
Data Index: 2458080 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.7488. Min Act: -0.1700
Data Index: 7105507 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.7488. Min Act: -0.1700
Data Index: 3404343 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1551. Min Range: -5.1551
Max Act: 4.7488. Min Act: -0.1700
Data Index: 4311698 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19