Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.5323. Min Act: -0.1700
Data Index: 1147006 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.3135. Min Act: -0.1700
Data Index: 979512 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.1885. Min Act: -0.1700
Data Index: 672524 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.1572. Min Act: -0.1700
Data Index: 7205990 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.1885. Min Act: -0.1700
Data Index: 8325262 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.1572. Min Act: -0.1700
Data Index: 1400678 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.1260. Min Act: -0.1700
Data Index: 320917 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.1572. Min Act: -0.1700
Data Index: 405322 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.1260. Min Act: -0.1700
Data Index: 2889465 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.1260. Min Act: -0.1700
Data Index: 571825 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0947. Min Act: -0.1700
Data Index: 1843224 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0635. Min Act: -0.1700
Data Index: 3964368 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0947. Min Act: -0.1700
Data Index: 2357900 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0947. Min Act: -0.1700
Data Index: 188009 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0947. Min Act: -0.1700
Data Index: 4672042 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0635. Min Act: -0.1700
Data Index: 4258962 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0635. Min Act: -0.1700
Data Index: 7590902 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0635. Min Act: -0.1700
Data Index: 7725936 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0635. Min Act: -0.1700
Data Index: 6859325 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5323. Min Range: -4.5323
Max Act: 4.0635. Min Act: -0.1700
Data Index: 8645615 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19