Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.9156. Min Act: -0.1700
Data Index: 7883092 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6969. Min Act: -0.1700
Data Index: 8614122 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5719. Min Act: -0.1700
Data Index: 7404401 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5719. Min Act: -0.1700
Data Index: 8540151 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5406. Min Act: -0.1700
Data Index: 8773786 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5406. Min Act: -0.1700
Data Index: 933551 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5406. Min Act: -0.1700
Data Index: 5515075 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5406. Min Act: -0.1700
Data Index: 4774523 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5406. Min Act: -0.1700
Data Index: 6482219 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5406. Min Act: -0.1700
Data Index: 7811701 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5094. Min Act: -0.1700
Data Index: 3693613 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.4781. Min Act: -0.1700
Data Index: 6390177 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.4781. Min Act: -0.1700
Data Index: 5331599 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5094. Min Act: -0.1700
Data Index: 8223354 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.4781. Min Act: -0.1700
Data Index: 6236872 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.4781. Min Act: -0.1700
Data Index: 2585127 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.4469. Min Act: -0.1700
Data Index: 125791 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.4469. Min Act: -0.1700
Data Index: 1701555 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.4156. Min Act: -0.1700
Data Index: 7898067 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.4469. Min Act: -0.1700
Data Index: 6082937 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19