Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 491 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.6847. Min Act: -0.1700
Data Index: 4245953 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.6534. Min Act: -0.1700
Data Index: 7456502 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.4812. Min Act: -0.1700
Data Index: 5511452 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.4028. Min Act: -0.1700
Data Index: 5787139 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.3871. Min Act: -0.1700
Data Index: 2786962 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.3714. Min Act: -0.1700
Data Index: 3131253 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.3087. Min Act: -0.1700
Data Index: 3717232 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2459. Min Act: -0.1700
Data Index: 2186152 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2459. Min Act: -0.1700
Data Index: 1228372 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2930. Min Act: -0.1700
Data Index: 4894675 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2773. Min Act: -0.1700
Data Index: 7834987 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2616. Min Act: -0.1700
Data Index: 1681440 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2616. Min Act: -0.1700
Data Index: 924113 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2616. Min Act: -0.1700
Data Index: 2481507 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2616. Min Act: -0.1700
Data Index: 3939370 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2301. Min Act: -0.1700
Data Index: 4833193 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2144. Min Act: -0.1700
Data Index: 2131352 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2459. Min Act: -0.1700
Data Index: 6504364 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2301. Min Act: -0.1700
Data Index: 2586979 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6847. Min Range: -3.6847
Max Act: 3.2301. Min Act: -0.1700
Data Index: 3361867 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19