Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4873 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.2272. Min Act: -0.1700
Data Index: 4861236 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.2272. Min Act: -0.1700
Data Index: 7738487 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.2272. Min Act: -0.1700
Data Index: 5807695 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.1959. Min Act: -0.1700
Data Index: 8277873 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.1647. Min Act: -0.1700
Data Index: 7041328 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.2272. Min Act: -0.1700
Data Index: 7165088 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.1647. Min Act: -0.1700
Data Index: 3165817 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.1334. Min Act: -0.1700
Data Index: 3838273 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.1022. Min Act: -0.1700
Data Index: 3165809 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.1022. Min Act: -0.1700
Data Index: 3165815 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.1022. Min Act: -0.1700
Data Index: 1009945 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.0709. Min Act: -0.1700
Data Index: 5106684 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.0709. Min Act: -0.1700
Data Index: 8331253 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.0709. Min Act: -0.1700
Data Index: 619431 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.0397. Min Act: -0.1700
Data Index: 3314781 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.0397. Min Act: -0.1700
Data Index: 3165807 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.0397. Min Act: -0.1700
Data Index: 7773619 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.0084. Min Act: -0.1700
Data Index: 3121340 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.0084. Min Act: -0.1700
Data Index: 5047358 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2272. Min Range: -5.2272
Max Act: 5.0397. Min Act: -0.1700
Data Index: 958939 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19