Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1365. Min Range: -5.1365
Max Act: 5.1365. Min Act: -0.1700
Data Index: 634259 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.9490. Min Act: -0.1700
Data Index: 3501762 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.8552. Min Act: -0.1700
Data Index: 440135 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.8240. Min Act: -0.1700
Data Index: 6455948 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.8240. Min Act: -0.1700
Data Index: 84955 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.7927. Min Act: -0.1700
Data Index: 1945002 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.8240. Min Act: -0.1700
Data Index: 7362366 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.7302. Min Act: -0.1700
Data Index: 4016425 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6990. Min Act: -0.1700
Data Index: 2955098 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6990. Min Act: -0.1700
Data Index: 4928413 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6990. Min Act: -0.1700
Data Index: 3582378 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6990. Min Act: -0.1700
Data Index: 8629937 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6990. Min Act: -0.1700
Data Index: 8031565 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6990. Min Act: -0.1700
Data Index: 7603868 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6677. Min Act: -0.1700
Data Index: 2592004 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6677. Min Act: -0.1700
Data Index: 118663 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6677. Min Act: -0.1700
Data Index: 3684292 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6052. Min Act: -0.1700
Data Index: 1886885 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6365. Min Act: -0.1700
Data Index: 2286938 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1365. Min Range: -5.1365
Max Act: 4.6365. Min Act: -0.1700
Data Index: 1975878 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19