Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 997 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2938. Min Range: -6.2938
Max Act: 6.2938. Min Act: -0.1700
Data Index: 7629972 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2938. Min Range: -6.2938
Max Act: 6.1063. Min Act: -0.1700
Data Index: 4197860 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2938. Min Range: -6.2938
Max Act: 6.1376. Min Act: -0.1700
Data Index: 335188 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2938. Min Range: -6.2938
Max Act: 6.0751. Min Act: -0.1700
Data Index: 7588335 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2938. Min Range: -6.2938
Max Act: 6.0438. Min Act: -0.1700
Data Index: 7402439 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2938. Min Range: -6.2938
Max Act: 6.0126. Min Act: -0.1700
Data Index: 5311992 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.9501. Min Act: -0.1700
Data Index: 6440443 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8876. Min Act: -0.1700
Data Index: 8109519 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8876. Min Act: -0.1700
Data Index: 8510627 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8876. Min Act: -0.1700
Data Index: 6587725 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.9188. Min Act: -0.1700
Data Index: 7057343 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8563. Min Act: -0.1700
Data Index: 4173655 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.9501. Min Act: -0.1700
Data Index: 4889710 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8563. Min Act: -0.1700
Data Index: 5800405 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8251. Min Act: -0.1700
Data Index: 8116885 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8876. Min Act: -0.1700
Data Index: 1986371 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8876. Min Act: -0.1700
Data Index: 3088581 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8876. Min Act: -0.1700
Data Index: 1511899 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.8876. Min Act: -0.1700
Data Index: 4899578 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2938. Min Range: -6.2938
Max Act: 5.7938. Min Act: -0.1700
Data Index: 6268146 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19