Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4688 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.6375. Min Act: -0.1700
Data Index: 2938941 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.3875. Min Act: -0.1700
Data Index: 4806605 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.3563. Min Act: -0.1700
Data Index: 1386827 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.2938. Min Act: -0.1700
Data Index: 3677514 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.2313. Min Act: -0.1700
Data Index: 8546166 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.2313. Min Act: -0.1700
Data Index: 5639932 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.2000. Min Act: -0.1700
Data Index: 4191738 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.2000. Min Act: -0.1700
Data Index: 6618694 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.2000. Min Act: -0.1700
Data Index: 8545806 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.1688. Min Act: -0.1700
Data Index: 3770863 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.1688. Min Act: -0.1700
Data Index: 929086 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.1375. Min Act: -0.1700
Data Index: 7472766 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.1375. Min Act: -0.1700
Data Index: 3770865 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.1063. Min Act: -0.1700
Data Index: 6227967 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.1063. Min Act: -0.1700
Data Index: 3104781 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.1063. Min Act: -0.1700
Data Index: 7411888 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.1063. Min Act: -0.1700
Data Index: 1722076 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.0750. Min Act: -0.1700
Data Index: 7942751 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.0750. Min Act: -0.1700
Data Index: 2205340 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6375. Min Range: -5.6375
Max Act: 5.1063. Min Act: -0.1700
Data Index: 2086727 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19