Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.8992. Min Act: -0.1700
Data Index: 1925300 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.6180. Min Act: -0.1700
Data Index: 4286500 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.5867. Min Act: -0.1700
Data Index: 4604914 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.5555. Min Act: -0.1700
Data Index: 298268 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.5242. Min Act: -0.1700
Data Index: 4433383 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.4617. Min Act: -0.1700
Data Index: 7310733 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.4617. Min Act: -0.1700
Data Index: 852081 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.4305. Min Act: -0.1700
Data Index: 7823216 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3992. Min Act: -0.1700
Data Index: 4323343 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3992. Min Act: -0.1700
Data Index: 2455458 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3680. Min Act: -0.1700
Data Index: 594751 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3992. Min Act: -0.1700
Data Index: 5044447 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3680. Min Act: -0.1700
Data Index: 7775675 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3680. Min Act: -0.1700
Data Index: 6269967 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3680. Min Act: -0.1700
Data Index: 5040031 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3055. Min Act: -0.1700
Data Index: 8079187 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3055. Min Act: -0.1700
Data Index: 3719272 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.3055. Min Act: -0.1700
Data Index: 7026617 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.2742. Min Act: -0.1700
Data Index: 1111720 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8992. Min Range: -6.8992
Max Act: 6.2742. Min Act: -0.1700
Data Index: 7550152 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19