Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5495 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5103. Min Range: -12.5103
Max Act: 12.5103. Min Act: -0.1700
Data Index: 1862825 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5103. Min Range: -12.5103
Max Act: 12.4478. Min Act: -0.1700
Data Index: 5827948 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5103. Min Range: -12.5103
Max Act: 12.2603. Min Act: -0.1700
Data Index: 2657122 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5103. Min Range: -12.5103
Max Act: 12.0728. Min Act: -0.1700
Data Index: 932240 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5103. Min Range: -12.5103
Max Act: 12.0103. Min Act: -0.1700
Data Index: 6319947 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.9478. Min Act: -0.1700
Data Index: 1027074 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.8853. Min Act: -0.1700
Data Index: 1623781 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.8853. Min Act: -0.1700
Data Index: 3816878 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.8853. Min Act: -0.1700
Data Index: 2845728 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.8853. Min Act: -0.1700
Data Index: 925081 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.8228. Min Act: -0.1700
Data Index: 2583563 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.8228. Min Act: -0.1700
Data Index: 4455971 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.8228. Min Act: -0.1700
Data Index: 6330520 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.7603. Min Act: -0.1700
Data Index: 783745 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.7603. Min Act: -0.1700
Data Index: 7163549 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.7603. Min Act: -0.1700
Data Index: 3850223 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.7603. Min Act: -0.1700
Data Index: 8485548 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.6978. Min Act: -0.1700
Data Index: 319247 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.6978. Min Act: -0.1700
Data Index: 715031 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5103. Min Range: -12.5103
Max Act: 11.6978. Min Act: -0.1700
Data Index: 1602961 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19