Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.5828. Min Act: -0.1700
Data Index: 1297086 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.5516. Min Act: -0.1700
Data Index: 1017998 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.4578. Min Act: -0.1700
Data Index: 6963711 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.3953. Min Act: -0.1700
Data Index: 3568986 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.3641. Min Act: -0.1700
Data Index: 4979898 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.3641. Min Act: -0.1700
Data Index: 4171364 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.3016. Min Act: -0.1700
Data Index: 8042621 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.2703. Min Act: -0.1700
Data Index: 2750729 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.2703. Min Act: -0.1700
Data Index: 1851964 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.2703. Min Act: -0.1700
Data Index: 6622039 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.2703. Min Act: -0.1700
Data Index: 4195877 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.2078. Min Act: -0.1700
Data Index: 1389844 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.2391. Min Act: -0.1700
Data Index: 6075269 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.1766. Min Act: -0.1700
Data Index: 583599 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.1453. Min Act: -0.1700
Data Index: 369121 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.1453. Min Act: -0.1700
Data Index: 6683401 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.0828. Min Act: -0.1700
Data Index: 3271096 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.0515. Min Act: -0.1700
Data Index: 1966317 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.0828. Min Act: -0.1700
Data Index: 7920798 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5828. Min Range: -4.5828
Max Act: 4.0828. Min Act: -0.1700
Data Index: 1973348 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19