Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6051 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.2857. Min Act: -0.1700
Data Index: 7895300 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.1920. Min Act: -0.1700
Data Index: 5084647 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.1607. Min Act: -0.1700
Data Index: 2998974 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.1607. Min Act: -0.1700
Data Index: 4935776 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0670. Min Act: -0.1700
Data Index: 380824 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0357. Min Act: -0.1700
Data Index: 3430201 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0357. Min Act: -0.1700
Data Index: 2311123 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0357. Min Act: -0.1700
Data Index: 489441 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0670. Min Act: -0.1700
Data Index: 7469965 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0045. Min Act: -0.1700
Data Index: 750972 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0045. Min Act: -0.1700
Data Index: 8214970 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0045. Min Act: -0.1700
Data Index: 2927993 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0045. Min Act: -0.1700
Data Index: 5173250 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0045. Min Act: -0.1700
Data Index: 3336577 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0045. Min Act: -0.1700
Data Index: 1039810 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9732. Min Act: -0.1700
Data Index: 1257791 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9420. Min Act: -0.1700
Data Index: 3913895 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9420. Min Act: -0.1700
Data Index: 2499549 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9420. Min Act: -0.1700
Data Index: 3212137 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9107. Min Act: -0.1700
Data Index: 828809 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19