Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4676 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.7355. Min Act: -0.1700
Data Index: 8104385 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.7195. Min Act: -0.1700
Data Index: 7832648 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.7195. Min Act: -0.1700
Data Index: 4704256 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.7035. Min Act: -0.1700
Data Index: 1423531 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.7035. Min Act: -0.1700
Data Index: 2751596 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.7035. Min Act: -0.1700
Data Index: 7426265 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6715. Min Act: -0.1700
Data Index: 4519951 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6875. Min Act: -0.1700
Data Index: 1269903 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6875. Min Act: -0.1700
Data Index: 7133132 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6554. Min Act: -0.1700
Data Index: 976943 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6715. Min Act: -0.1700
Data Index: 1221147 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6715. Min Act: -0.1700
Data Index: 2428220 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6554. Min Act: -0.1700
Data Index: 5419074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6554. Min Act: -0.1700
Data Index: 8721478 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6394. Min Act: -0.1700
Data Index: 4703555 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6233. Min Act: -0.1700
Data Index: 8798351 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6233. Min Act: -0.1700
Data Index: 4900052 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6394. Min Act: -0.1700
Data Index: 4638768 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.6233. Min Act: -0.1700
Data Index: 1580678 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7355. Min Range: -2.7355
Max Act: 2.5911. Min Act: -0.1700
Data Index: 2654542 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19