Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.6022. Min Act: -0.1700
Data Index: 6198737 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.5084. Min Act: -0.1700
Data Index: 4683282 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.4772. Min Act: -0.1700
Data Index: 5282727 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.4147. Min Act: -0.1700
Data Index: 8445035 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.2897. Min Act: -0.1700
Data Index: 1487410 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.2897. Min Act: -0.1700
Data Index: 4965161 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.2272. Min Act: -0.1700
Data Index: 3696619 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1959. Min Act: -0.1700
Data Index: 6501243 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1647. Min Act: -0.1700
Data Index: 3393412 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1334. Min Act: -0.1700
Data Index: 2309696 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1334. Min Act: -0.1700
Data Index: 6072176 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1334. Min Act: -0.1700
Data Index: 1476609 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1022. Min Act: -0.1700
Data Index: 3496310 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1022. Min Act: -0.1699
Data Index: 3581022 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1022. Min Act: -0.1700
Data Index: 1487409 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1022. Min Act: -0.1700
Data Index: 4145193 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.0709. Min Act: -0.1700
Data Index: 28549 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.1022. Min Act: -0.1700
Data Index: 7540408 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.0397. Min Act: -0.1700
Data Index: 1326309 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6022. Min Range: -5.6022
Max Act: 5.0397. Min Act: -0.1700
Data Index: 6334687 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19