Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.2247. Min Act: -0.1700
Data Index: 2191558 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.1622. Min Act: -0.1700
Data Index: 119821 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.9435. Min Act: -0.1700
Data Index: 8038168 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.8810. Min Act: -0.1700
Data Index: 5209635 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.8810. Min Act: -0.1700
Data Index: 6563372 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.8810. Min Act: -0.1700
Data Index: 1344462 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.8497. Min Act: -0.1700
Data Index: 3364519 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.8185. Min Act: -0.1700
Data Index: 3364517 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.7872. Min Act: -0.1700
Data Index: 7345522 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.7560. Min Act: -0.1700
Data Index: 1396708 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.7560. Min Act: -0.1700
Data Index: 1692216 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.7247. Min Act: -0.1700
Data Index: 533799 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.6935. Min Act: -0.1700
Data Index: 4581282 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.6622. Min Act: -0.1700
Data Index: 708415 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.6935. Min Act: -0.1700
Data Index: 2255668 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.6310. Min Act: -0.1700
Data Index: 3648217 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.6310. Min Act: -0.1700
Data Index: 6097341 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.6310. Min Act: -0.1700
Data Index: 1364564 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.6310. Min Act: -0.1700
Data Index: 5759369 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.6310. Min Act: -0.1700
Data Index: 1186714 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19