Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2301 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1353. Min Range: -8.1353
Max Act: 8.1353. Min Act: -0.1700
Data Index: 6024228 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1353. Min Range: -8.1353
Max Act: 8.0728. Min Act: -0.1700
Data Index: 7008534 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.9165. Min Act: -0.1700
Data Index: 6693355 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.8853. Min Act: -0.1700
Data Index: 4002397 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.8540. Min Act: -0.1700
Data Index: 5248493 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.8540. Min Act: -0.1700
Data Index: 6402054 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.8228. Min Act: -0.1700
Data Index: 5662583 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.7603. Min Act: -0.1700
Data Index: 1215812 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.7290. Min Act: -0.1700
Data Index: 8398059 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.7603. Min Act: -0.1700
Data Index: 1132252 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.6978. Min Act: -0.1700
Data Index: 217568 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.6978. Min Act: -0.1700
Data Index: 1686429 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.6978. Min Act: -0.1700
Data Index: 3870394 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.7290. Min Act: -0.1700
Data Index: 8718528 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.6665. Min Act: -0.1700
Data Index: 4878526 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.6353. Min Act: -0.1700
Data Index: 3072386 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.6353. Min Act: -0.1700
Data Index: 6967074 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.6353. Min Act: -0.1700
Data Index: 2074652 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.6040. Min Act: -0.1700
Data Index: 3758786 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1353. Min Range: -8.1353
Max Act: 7.6353. Min Act: -0.1700
Data Index: 7564340 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19