Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1346. Min Range: -8.1346
Max Act: 8.1346. Min Act: -0.1700
Data Index: 4473140 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.6034. Min Act: -0.1700
Data Index: 3282647 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.5721. Min Act: -0.1700
Data Index: 2902320 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.4784. Min Act: -0.1700
Data Index: 3800779 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.4471. Min Act: -0.1700
Data Index: 6198030 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.3534. Min Act: -0.1700
Data Index: 5883730 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.3534. Min Act: -0.1700
Data Index: 5043350 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.2909. Min Act: -0.1700
Data Index: 7363531 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.2596. Min Act: -0.1700
Data Index: 7484274 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.1971. Min Act: -0.1700
Data Index: 613265 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.1971. Min Act: -0.1700
Data Index: 1762423 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.2284. Min Act: -0.1700
Data Index: 111066 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.1659. Min Act: -0.1700
Data Index: 7536668 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.1659. Min Act: -0.1700
Data Index: 3335930 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.1034. Min Act: -0.1700
Data Index: 1574407 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.0409. Min Act: -0.1700
Data Index: 6212498 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.0096. Min Act: -0.1700
Data Index: 5868087 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.0096. Min Act: -0.1700
Data Index: 6669751 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1346. Min Range: -8.1346
Max Act: 7.0096. Min Act: -0.1700
Data Index: 288590 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1346. Min Range: -8.1346
Max Act: 6.9784. Min Act: -0.1700
Data Index: 1481050 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19