Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 954 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.7513. Min Act: -0.1700
Data Index: 3665064 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.8138. Min Act: -0.1700
Data Index: 8326799 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.7513. Min Act: -0.1700
Data Index: 1660524 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.6888. Min Act: -0.1700
Data Index: 3066313 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.3763. Min Act: -0.1700
Data Index: 1977764 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.2200. Min Act: -0.1700
Data Index: 356622 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.1888. Min Act: -0.1700
Data Index: 2340401 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.2200. Min Act: -0.1700
Data Index: 1329003 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.2200. Min Act: -0.1700
Data Index: 5158506 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.2200. Min Act: -0.1700
Data Index: 4063816 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.1263. Min Act: -0.1700
Data Index: 4007414 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.2200. Min Act: -0.1700
Data Index: 4370225 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.1575. Min Act: -0.1700
Data Index: 7441629 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.1575. Min Act: -0.1700
Data Index: 1892875 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.1575. Min Act: -0.1700
Data Index: 4794761 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.1263. Min Act: -0.1700
Data Index: 7682402 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.0325. Min Act: -0.1700
Data Index: 6067843 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.0950. Min Act: -0.1700
Data Index: 1129892 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.0950. Min Act: -0.1700
Data Index: 4631170 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8138. Min Range: -8.8138
Max Act: 8.0950. Min Act: -0.1700
Data Index: 2213434 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19