Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.5192. Min Act: -0.1700
Data Index: 5286989 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.5192. Min Act: -0.1700
Data Index: 2528786 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.4255. Min Act: -0.1700
Data Index: 1213332 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.3005. Min Act: -0.1700
Data Index: 3259263 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.2692. Min Act: -0.1700
Data Index: 5672222 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.2379. Min Act: -0.1700
Data Index: 7571687 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.2379. Min Act: -0.1700
Data Index: 5380674 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.2067. Min Act: -0.1700
Data Index: 8185673 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.2067. Min Act: -0.1700
Data Index: 5126226 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.2067. Min Act: -0.1700
Data Index: 5215140 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1442. Min Act: -0.1700
Data Index: 7369276 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1754. Min Act: -0.1700
Data Index: 5901325 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1754. Min Act: -0.1700
Data Index: 1892702 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1129. Min Act: -0.1700
Data Index: 3007547 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1442. Min Act: -0.1700
Data Index: 944092 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1754. Min Act: -0.1700
Data Index: 4904792 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1442. Min Act: -0.1700
Data Index: 228185 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1129. Min Act: -0.1700
Data Index: 7379255 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1129. Min Act: -0.1700
Data Index: 392245 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5192. Min Range: -4.5192
Max Act: 4.1129. Min Act: -0.1700
Data Index: 7828053 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19