Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3847. Min Range: -6.3847
Max Act: 6.3847. Min Act: -0.1700
Data Index: 709547 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3847. Min Range: -6.3847
Max Act: 6.2284. Min Act: -0.1700
Data Index: 5140698 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3847. Min Range: -6.3847
Max Act: 6.1972. Min Act: -0.1700
Data Index: 1532803 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3847. Min Range: -6.3847
Max Act: 6.1659. Min Act: -0.1700
Data Index: 4682456 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3847. Min Range: -6.3847
Max Act: 6.1347. Min Act: -0.1700
Data Index: 1713260 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3847. Min Range: -6.3847
Max Act: 6.0097. Min Act: -0.1700
Data Index: 3960942 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.9784. Min Act: -0.1700
Data Index: 847024 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.9472. Min Act: -0.1700
Data Index: 6105206 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.9472. Min Act: -0.1700
Data Index: 5522829 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8847. Min Act: -0.1700
Data Index: 435251 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8847. Min Act: -0.1700
Data Index: 3999746 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8847. Min Act: -0.1700
Data Index: 5934648 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8847. Min Act: -0.1700
Data Index: 2437675 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8534. Min Act: -0.1700
Data Index: 2131715 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8222. Min Act: -0.1700
Data Index: 4544318 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8534. Min Act: -0.1700
Data Index: 7656333 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8222. Min Act: -0.1700
Data Index: 5619688 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8222. Min Act: -0.1700
Data Index: 3204409 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.8222. Min Act: -0.1700
Data Index: 5954468 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3847. Min Range: -6.3847
Max Act: 5.7909. Min Act: -0.1700
Data Index: 3121758 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19