Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 819 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.5336. Min Act: -0.1700
Data Index: 4210011 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.3774. Min Act: -0.1700
Data Index: 4618742 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.2211. Min Act: -0.1700
Data Index: 4304717 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.2211. Min Act: -0.1700
Data Index: 8396453 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.1899. Min Act: -0.1700
Data Index: 782348 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.1586. Min Act: -0.1700
Data Index: 2658754 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.1274. Min Act: -0.1700
Data Index: 5443625 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.0649. Min Act: -0.1700
Data Index: 2985892 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.0649. Min Act: -0.1700
Data Index: 8458762 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.0336. Min Act: -0.1700
Data Index: 1038189 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.0024. Min Act: -0.1700
Data Index: 575993 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5336. Min Range: -6.5336
Max Act: 6.0024. Min Act: -0.1700
Data Index: 8446763 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5336. Min Range: -6.5336
Max Act: 5.9711. Min Act: -0.1700
Data Index: 8825168 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5336. Min Range: -6.5336
Max Act: 5.9399. Min Act: -0.1700
Data Index: 853296 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5336. Min Range: -6.5336
Max Act: 5.9086. Min Act: -0.1700
Data Index: 7692436 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5336. Min Range: -6.5336
Max Act: 5.8774. Min Act: -0.1700
Data Index: 7042891 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5336. Min Range: -6.5336
Max Act: 5.8774. Min Act: -0.1700
Data Index: 8640487 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5336. Min Range: -6.5336
Max Act: 5.8461. Min Act: -0.1700
Data Index: 7379337 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5336. Min Range: -6.5336
Max Act: 5.8461. Min Act: -0.1700
Data Index: 7053880 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5336. Min Range: -6.5336
Max Act: 5.8149. Min Act: -0.1700
Data Index: 8446762 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19