Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.3260. Min Act: -0.1700
Data Index: 3240753 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.2010. Min Act: -0.1700
Data Index: 6296184 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1697. Min Act: -0.1700
Data Index: 7773320 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1697. Min Act: -0.1700
Data Index: 4354497 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1385. Min Act: -0.1700
Data Index: 5302360 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1385. Min Act: -0.1700
Data Index: 237839 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 4660107 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 6161672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 2109545 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 3934278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 1776973 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.0759. Min Act: -0.1700
Data Index: 5953566 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 5695280 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 7680270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 7576917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 7191433 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 6812798 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 5278786 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.0759. Min Act: -0.1700
Data Index: 4774905 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3260. Min Range: -4.3260
Max Act: 4.1072. Min Act: -0.1700
Data Index: 6775195 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19