Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5994 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.9166. Min Act: -0.1700
Data Index: 676266 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.8541. Min Act: -0.1700
Data Index: 3601740 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.8541. Min Act: -0.1700
Data Index: 6635915 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.7603. Min Act: -0.1700
Data Index: 525314 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.7916. Min Act: -0.1700
Data Index: 8389749 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.7916. Min Act: -0.1700
Data Index: 3120615 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.7603. Min Act: -0.1700
Data Index: 6176683 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.6978. Min Act: -0.1700
Data Index: 5017785 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.7291. Min Act: -0.1700
Data Index: 6364314 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.6978. Min Act: -0.1700
Data Index: 8212503 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.6666. Min Act: -0.1700
Data Index: 4669247 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.6666. Min Act: -0.1700
Data Index: 3323838 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.6353. Min Act: -0.1700
Data Index: 66940 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.6353. Min Act: -0.1700
Data Index: 5723000 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.6353. Min Act: -0.1700
Data Index: 5900440 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.5728. Min Act: -0.1700
Data Index: 8379671 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.5416. Min Act: -0.1700
Data Index: 304527 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.5728. Min Act: -0.1700
Data Index: 2641093 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.5728. Min Act: -0.1700
Data Index: 2873367 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9166. Min Range: -7.9166
Max Act: 7.5416. Min Act: -0.1700
Data Index: 7352581 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19