Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1334. Min Range: -5.1334
Max Act: 5.1334. Min Act: -0.1700
Data Index: 78664 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1334. Min Range: -5.1334
Max Act: 5.1334. Min Act: -0.1700
Data Index: 7560812 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1334. Min Range: -5.1334
Max Act: 5.0709. Min Act: -0.1700
Data Index: 7467950 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1334. Min Range: -5.1334
Max Act: 5.0709. Min Act: -0.1700
Data Index: 2714077 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1334. Min Range: -5.1334
Max Act: 5.0397. Min Act: -0.1700
Data Index: 1936292 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1334. Min Range: -5.1334
Max Act: 5.0397. Min Act: -0.1700
Data Index: 7316451 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1334. Min Range: -5.1334
Max Act: 5.0084. Min Act: -0.1700
Data Index: 5399737 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.9459. Min Act: -0.1700
Data Index: 1549483 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.9147. Min Act: -0.1700
Data Index: 4815360 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.8522. Min Act: -0.1700
Data Index: 8578433 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.9147. Min Act: -0.1700
Data Index: 7309058 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.8522. Min Act: -0.1700
Data Index: 8486398 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.8834. Min Act: -0.1700
Data Index: 8365504 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.8834. Min Act: -0.1700
Data Index: 8094881 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.8522. Min Act: -0.1700
Data Index: 629755 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.8209. Min Act: -0.1700
Data Index: 7748210 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.8522. Min Act: -0.1700
Data Index: 175754 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.7897. Min Act: -0.1700
Data Index: 5527041 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.8209. Min Act: -0.1700
Data Index: 8231946 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1334. Min Range: -5.1334
Max Act: 4.8209. Min Act: -0.1700
Data Index: 5149748 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19