Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 51 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.9226. Min Act: -0.1700
Data Index: 3531863 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.8601. Min Act: -0.1700
Data Index: 5309076 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.7664. Min Act: -0.1700
Data Index: 3531858 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.7039. Min Act: -0.1700
Data Index: 5309078 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.4539. Min Act: -0.1700
Data Index: 4954515 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.4539. Min Act: -0.1700
Data Index: 4954505 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.4226. Min Act: -0.1700
Data Index: 950491 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.4539. Min Act: -0.1700
Data Index: 5245326 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.3914. Min Act: -0.1700
Data Index: 5309080 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.3601. Min Act: -0.1700
Data Index: 7393329 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.2976. Min Act: -0.1700
Data Index: 532753 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.2976. Min Act: -0.1700
Data Index: 7214120 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.2976. Min Act: -0.1700
Data Index: 532757 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.2664. Min Act: -0.1700
Data Index: 8084609 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.2351. Min Act: -0.1700
Data Index: 3521911 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.2351. Min Act: -0.1700
Data Index: 7088562 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.2039. Min Act: -0.1700
Data Index: 5289761 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.2351. Min Act: -0.1700
Data Index: 4348323 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.1726. Min Act: -0.1700
Data Index: 950492 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9226. Min Range: -5.9226
Max Act: 5.1414. Min Act: -0.1700
Data Index: 1577619 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19