Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.9704. Min Act: -0.1700
Data Index: 7113027 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.9391. Min Act: -0.1700
Data Index: 38790 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8766. Min Act: -0.1700
Data Index: 1802567 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8766. Min Act: -0.1700
Data Index: 8690684 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8297. Min Act: -0.1700
Data Index: 6632061 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8140. Min Act: -0.1700
Data Index: 8281421 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8140. Min Act: -0.1700
Data Index: 2906491 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8140. Min Act: -0.1700
Data Index: 8498129 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7984. Min Act: -0.1700
Data Index: 2354234 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7984. Min Act: -0.1700
Data Index: 4609157 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7828. Min Act: -0.1700
Data Index: 4211586 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7671. Min Act: -0.1700
Data Index: 6115452 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7515. Min Act: -0.1700
Data Index: 6655974 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7515. Min Act: -0.1700
Data Index: 5408952 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7515. Min Act: -0.1700
Data Index: 2955762 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7202. Min Act: -0.1700
Data Index: 7538281 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7359. Min Act: -0.1700
Data Index: 4908793 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7202. Min Act: -0.1700
Data Index: 2354231 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7202. Min Act: -0.1700
Data Index: 4680573 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7046. Min Act: -0.1700
Data Index: 4525332 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19