Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2369 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1202. Min Range: -3.1202
Max Act: 3.1202. Min Act: -0.1700
Data Index: 6390627 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1202. Min Range: -3.1202
Max Act: 3.0729. Min Act: -0.1700
Data Index: 3079321 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1202. Min Range: -3.1202
Max Act: 3.0571. Min Act: -0.1700
Data Index: 1985017 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1202. Min Range: -3.1202
Max Act: 3.0729. Min Act: -0.1700
Data Index: 6265473 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1202. Min Range: -3.1202
Max Act: 3.0414. Min Act: -0.1700
Data Index: 8448475 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1202. Min Range: -3.1202
Max Act: 3.0256. Min Act: -0.1700
Data Index: 1334003 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.9940. Min Act: -0.1700
Data Index: 7110446 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.9782. Min Act: -0.1700
Data Index: 6578981 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.9465. Min Act: -0.1700
Data Index: 4314925 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.9623. Min Act: -0.1700
Data Index: 2085564 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.9307. Min Act: -0.1700
Data Index: 1884063 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.8990. Min Act: -0.1700
Data Index: 6656012 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.9148. Min Act: -0.1700
Data Index: 5068270 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.9148. Min Act: -0.1700
Data Index: 5588459 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.8672. Min Act: -0.1700
Data Index: 4541956 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.8672. Min Act: -0.1700
Data Index: 6945450 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.8831. Min Act: -0.1700
Data Index: 401534 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.8831. Min Act: -0.1700
Data Index: 934321 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.8514. Min Act: -0.1700
Data Index: 1840197 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1202. Min Range: -3.1202
Max Act: 2.8514. Min Act: -0.1700
Data Index: 3463596 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19