Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.9759. Min Act: -0.1700
Data Index: 6816311 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.8509. Min Act: -0.1700
Data Index: 7050823 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.6947. Min Act: -0.1700
Data Index: 2500797 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.6634. Min Act: -0.1700
Data Index: 2835972 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.6322. Min Act: -0.1700
Data Index: 7050828 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.6322. Min Act: -0.1700
Data Index: 5553374 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5697. Min Act: -0.1700
Data Index: 8293728 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5697. Min Act: -0.1700
Data Index: 7173635 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5384. Min Act: -0.1700
Data Index: 6503210 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5072. Min Act: -0.1700
Data Index: 5841899 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5384. Min Act: -0.1700
Data Index: 3708610 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5072. Min Act: -0.1700
Data Index: 6343357 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5384. Min Act: -0.1700
Data Index: 4965525 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5072. Min Act: -0.1700
Data Index: 7875532 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5072. Min Act: -0.1700
Data Index: 5132062 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.4447. Min Act: -0.1700
Data Index: 32280 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.4759. Min Act: -0.1700
Data Index: 3279247 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.4759. Min Act: -0.1700
Data Index: 1379021 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.4447. Min Act: -0.1700
Data Index: 573230 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.4447. Min Act: -0.1700
Data Index: 6912488 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19