Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2895 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.5224. Min Act: -0.1700
Data Index: 3418398 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.5224. Min Act: -0.1700
Data Index: 5475324 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.5224. Min Act: -0.1700
Data Index: 7541673 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.3349. Min Act: -0.1700
Data Index: 4791802 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.2724. Min Act: -0.1700
Data Index: 3350517 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.2724. Min Act: -0.1700
Data Index: 2251396 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.2099. Min Act: -0.1700
Data Index: 2042073 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.2724. Min Act: -0.1700
Data Index: 2064689 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.0849. Min Act: -0.1700
Data Index: 1798785 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.1162. Min Act: -0.1700
Data Index: 5392447 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.1162. Min Act: -0.1700
Data Index: 80651 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.0849. Min Act: -0.1700
Data Index: 2772291 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.0537. Min Act: -0.1700
Data Index: 6124388 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5224. Min Range: -8.5224
Max Act: 8.0537. Min Act: -0.1700
Data Index: 3392087 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5224. Min Range: -8.5224
Max Act: 7.9599. Min Act: -0.1700
Data Index: 8803324 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5224. Min Range: -8.5224
Max Act: 7.9599. Min Act: -0.1700
Data Index: 2677276 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5224. Min Range: -8.5224
Max Act: 7.9912. Min Act: -0.1700
Data Index: 715238 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5224. Min Range: -8.5224
Max Act: 7.9599. Min Act: -0.1700
Data Index: 5725122 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5224. Min Range: -8.5224
Max Act: 7.8974. Min Act: -0.1700
Data Index: 5725970 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5224. Min Range: -8.5224
Max Act: 7.8974. Min Act: -0.1700
Data Index: 6913814 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19