Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.5433. Min Act: -0.1700
Data Index: 6351746 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.3246. Min Act: -0.1700
Data Index: 6941524 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.2621. Min Act: -0.1700
Data Index: 5215063 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.1996. Min Act: -0.1700
Data Index: 919391 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.1996. Min Act: -0.1700
Data Index: 6221973 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.1996. Min Act: -0.1700
Data Index: 6557253 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.1058. Min Act: -0.1700
Data Index: 7668775 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.1371. Min Act: -0.1700
Data Index: 6484410 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.1058. Min Act: -0.1700
Data Index: 5234741 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.1058. Min Act: -0.1700
Data Index: 318502 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.1371. Min Act: -0.1700
Data Index: 922916 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.0746. Min Act: -0.1700
Data Index: 3934715 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.0746. Min Act: -0.1700
Data Index: 5034503 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.0746. Min Act: -0.1700
Data Index: 7415756 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.0746. Min Act: -0.1700
Data Index: 1161658 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.0746. Min Act: -0.1700
Data Index: 3063339 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.0746. Min Act: -0.1700
Data Index: 881774 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.0433. Min Act: -0.1700
Data Index: 7542820 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5433. Min Range: -6.5433
Max Act: 6.0121. Min Act: -0.1700
Data Index: 7956044 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5433. Min Range: -6.5433
Max Act: 5.9808. Min Act: -0.1700
Data Index: 1826031 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19