Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4891 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.7535. Min Act: -0.1700
Data Index: 1735903 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.7535. Min Act: -0.1700
Data Index: 4925094 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.6285. Min Act: -0.1700
Data Index: 8593959 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.5347. Min Act: -0.1700
Data Index: 7552745 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.4722. Min Act: -0.1700
Data Index: 15022 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.4410. Min Act: -0.1700
Data Index: 5150376 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.4097. Min Act: -0.1700
Data Index: 3009025 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.3785. Min Act: -0.1700
Data Index: 6644773 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.4097. Min Act: -0.1700
Data Index: 7133613 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.4097. Min Act: -0.1700
Data Index: 2716104 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.3785. Min Act: -0.1700
Data Index: 7216850 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.3785. Min Act: -0.1700
Data Index: 7780635 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.3785. Min Act: -0.1700
Data Index: 4185170 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.3472. Min Act: -0.1700
Data Index: 6950039 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.3472. Min Act: -0.1700
Data Index: 2280234 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.2847. Min Act: -0.1700
Data Index: 3908681 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.2847. Min Act: -0.1700
Data Index: 3867572 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.2847. Min Act: -0.1700
Data Index: 3417727 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.2535. Min Act: -0.1700
Data Index: 5395333 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7535. Min Range: -5.7535
Max Act: 5.2535. Min Act: -0.1700
Data Index: 5525698 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19