Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4622 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.6871. Min Act: -0.1700
Data Index: 759206 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.4996. Min Act: -0.1700
Data Index: 4679245 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.3746. Min Act: -0.1700
Data Index: 4590443 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.3433. Min Act: -0.1700
Data Index: 2842478 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.3746. Min Act: -0.1700
Data Index: 8195422 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.3433. Min Act: -0.1700
Data Index: 1844187 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.3433. Min Act: -0.1700
Data Index: 3620984 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.3121. Min Act: -0.1700
Data Index: 3868096 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.3121. Min Act: -0.1700
Data Index: 334692 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.2340. Min Act: -0.1700
Data Index: 1090820 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.1714. Min Act: -0.1700
Data Index: 3020383 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.2027. Min Act: -0.1700
Data Index: 883841 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.2183. Min Act: -0.1700
Data Index: 4417111 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.1714. Min Act: -0.1700
Data Index: 2126848 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.1871. Min Act: -0.1700
Data Index: 2471903 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.1558. Min Act: -0.1700
Data Index: 2754994 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.1402. Min Act: -0.1700
Data Index: 7169110 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.1402. Min Act: -0.1700
Data Index: 6908318 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.1402. Min Act: -0.1700
Data Index: 7261528 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6871. Min Range: -4.6871
Max Act: 4.1246. Min Act: -0.1700
Data Index: 1743445 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19