Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1987. Min Range: -2.1987
Max Act: 2.1987. Min Act: -0.1700
Data Index: 2220282 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1987. Min Range: -2.1987
Max Act: 2.0483. Min Act: -0.1700
Data Index: 244335 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.9978. Min Act: -0.1700
Data Index: 7529744 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.9639. Min Act: -0.1700
Data Index: 5107874 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.9639. Min Act: -0.1700
Data Index: 4646478 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.9639. Min Act: -0.1700
Data Index: 5265450 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.9129. Min Act: -0.1700
Data Index: 2720763 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.9299. Min Act: -0.1700
Data Index: 5783834 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8959. Min Act: -0.1700
Data Index: 5531309 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.9299. Min Act: -0.1700
Data Index: 6495647 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8959. Min Act: -0.1700
Data Index: 7268925 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8617. Min Act: -0.1700
Data Index: 6351984 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8788. Min Act: -0.1700
Data Index: 8342275 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8617. Min Act: -0.1700
Data Index: 5072554 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8788. Min Act: -0.1700
Data Index: 1908872 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8446. Min Act: -0.1700
Data Index: 7313464 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8617. Min Act: -0.1700
Data Index: 4891602 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8617. Min Act: -0.1700
Data Index: 3105838 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8446. Min Act: -0.1700
Data Index: 4495038 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1987. Min Range: -2.1987
Max Act: 1.8274. Min Act: -0.1700
Data Index: 963558 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19