Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2359 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.5078. Min Act: -0.1700
Data Index: 3717989 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.5390. Min Act: -0.1700
Data Index: 1954057 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3828. Min Act: -0.1700
Data Index: 8492161 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3828. Min Act: -0.1700
Data Index: 4466038 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3515. Min Act: -0.1700
Data Index: 933247 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3515. Min Act: -0.1700
Data Index: 5507864 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3203. Min Act: -0.1700
Data Index: 6093982 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.2890. Min Act: -0.1700
Data Index: 6126687 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3203. Min Act: -0.1700
Data Index: 5979268 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.2578. Min Act: -0.1700
Data Index: 3086477 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.2578. Min Act: -0.1700
Data Index: 7047968 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.2578. Min Act: -0.1700
Data Index: 8212892 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.2265. Min Act: -0.1700
Data Index: 7009895 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.2265. Min Act: -0.1700
Data Index: 7384611 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.1953. Min Act: -0.1700
Data Index: 6905133 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.1953. Min Act: -0.1700
Data Index: 171322 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.1640. Min Act: -0.1700
Data Index: 7760050 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.1640. Min Act: -0.1700
Data Index: 6886268 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.1640. Min Act: -0.1700
Data Index: 6818721 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.1328. Min Act: -0.1700
Data Index: 5300403 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19