Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4211 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0092. Min Range: -5.0092
Max Act: 5.0092. Min Act: -0.1700
Data Index: 2006708 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8842. Min Act: -0.1700
Data Index: 3171853 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8530. Min Act: -0.1700
Data Index: 652241 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 6507057 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6967. Min Act: -0.1700
Data Index: 6967663 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6967. Min Act: -0.1700
Data Index: 966330 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6655. Min Act: -0.1700
Data Index: 2819626 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6655. Min Act: -0.1700
Data Index: 1718430 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6342. Min Act: -0.1700
Data Index: 2390285 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5717. Min Act: -0.1700
Data Index: 103955 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5404. Min Act: -0.1700
Data Index: 8137264 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5717. Min Act: -0.1700
Data Index: 2086534 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5092. Min Act: -0.1700
Data Index: 2323973 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5404. Min Act: -0.1700
Data Index: 5816150 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5092. Min Act: -0.1700
Data Index: 1670526 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5404. Min Act: -0.1700
Data Index: 5045762 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5404. Min Act: -0.1700
Data Index: 7362337 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5404. Min Act: -0.1700
Data Index: 7336487 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5404. Min Act: -0.1700
Data Index: 5681926 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5092. Min Act: -0.1700
Data Index: 6644833 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19