Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.9474. Min Act: -0.1700
Data Index: 5769147 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.8998. Min Act: -0.1700
Data Index: 6748295 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.7727. Min Act: -0.1700
Data Index: 219574 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.7088. Min Act: -0.1698
Data Index: 7062009 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6928. Min Act: -0.1700
Data Index: 8478125 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6768. Min Act: -0.1700
Data Index: 2581012 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6447. Min Act: -0.1700
Data Index: 3273769 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6286. Min Act: -0.1700
Data Index: 6524771 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6286. Min Act: -0.1700
Data Index: 6245763 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6286. Min Act: -0.1700
Data Index: 6090162 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6125. Min Act: -0.1700
Data Index: 4386135 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6125. Min Act: -0.1700
Data Index: 4187690 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6125. Min Act: -0.1700
Data Index: 3844098 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.6125. Min Act: -0.1700
Data Index: 8186508 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.5965. Min Act: -0.1700
Data Index: 2357336 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.5965. Min Act: -0.1700
Data Index: 1516682 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.5803. Min Act: -0.1700
Data Index: 6182945 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.5803. Min Act: -0.1700
Data Index: 7376505 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.5803. Min Act: -0.1700
Data Index: 8129136 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9474. Min Range: -2.9474
Max Act: 2.5803. Min Act: -0.1700
Data Index: 5515682 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19