Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0406. Min Range: -6.0406
Max Act: 6.0406. Min Act: -0.1700
Data Index: 92916 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.9156. Min Act: -0.1700
Data Index: 5195300 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.7593. Min Act: -0.1700
Data Index: 5553003 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.7593. Min Act: -0.1700
Data Index: 981330 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.7593. Min Act: -0.1700
Data Index: 5751016 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6968. Min Act: -0.1700
Data Index: 4737008 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6656. Min Act: -0.1700
Data Index: 1761727 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.7281. Min Act: -0.1700
Data Index: 7479908 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6968. Min Act: -0.1700
Data Index: 437747 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6656. Min Act: -0.1700
Data Index: 8037910 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6031. Min Act: -0.1700
Data Index: 7694823 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6031. Min Act: -0.1700
Data Index: 4624915 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6343. Min Act: -0.1700
Data Index: 6271030 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6343. Min Act: -0.1700
Data Index: 2162450 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6031. Min Act: -0.1700
Data Index: 972260 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.5718. Min Act: -0.1700
Data Index: 2112180 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.6031. Min Act: -0.1700
Data Index: 1092572 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.5406. Min Act: -0.1700
Data Index: 2037717 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.5718. Min Act: -0.1700
Data Index: 5114156 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0406. Min Range: -6.0406
Max Act: 5.5718. Min Act: -0.1700
Data Index: 4465346 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19