Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4995 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.5871. Min Act: -0.1700
Data Index: 3416638 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.4621. Min Act: -0.1700
Data Index: 8743288 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3683. Min Act: -0.1700
Data Index: 5143984 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3371. Min Act: -0.1700
Data Index: 5031303 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3371. Min Act: -0.1700
Data Index: 2693381 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3371. Min Act: -0.1700
Data Index: 6948473 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3371. Min Act: -0.1700
Data Index: 7782998 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3058. Min Act: -0.1700
Data Index: 6579695 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3058. Min Act: -0.1700
Data Index: 7645307 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3058. Min Act: -0.1700
Data Index: 2823359 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2746. Min Act: -0.1700
Data Index: 8265323 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2433. Min Act: -0.1700
Data Index: 1586223 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2433. Min Act: -0.1700
Data Index: 2977809 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2433. Min Act: -0.1700
Data Index: 8125030 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2433. Min Act: -0.1700
Data Index: 8829045 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2433. Min Act: -0.1700
Data Index: 4953206 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2433. Min Act: -0.1700
Data Index: 4867060 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2121. Min Act: -0.1700
Data Index: 6957427 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.1808. Min Act: -0.1700
Data Index: 2806051 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.1808. Min Act: -0.1700
Data Index: 513673 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19