Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 857 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.4415. Min Act: -0.1700
Data Index: 4213251 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.4415. Min Act: -0.1700
Data Index: 2764975 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.4415. Min Act: -0.1700
Data Index: 6830698 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.4102. Min Act: -0.1700
Data Index: 1186325 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.3790. Min Act: -0.1700
Data Index: 6410713 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.3790. Min Act: -0.1700
Data Index: 6533138 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.3790. Min Act: -0.1700
Data Index: 6281402 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.3790. Min Act: -0.1700
Data Index: 1859049 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.3477. Min Act: -0.1700
Data Index: 616115 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.3165. Min Act: -0.1700
Data Index: 2822261 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.2852. Min Act: -0.1700
Data Index: 8685046 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.3165. Min Act: -0.1700
Data Index: 5015123 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.2852. Min Act: -0.1700
Data Index: 766252 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.2540. Min Act: -0.1700
Data Index: 706845 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.2227. Min Act: -0.1700
Data Index: 3738914 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.1602. Min Act: -0.1700
Data Index: 6759527 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.1602. Min Act: -0.1700
Data Index: 4777884 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.1602. Min Act: -0.1700
Data Index: 2198723 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.1602. Min Act: -0.1700
Data Index: 3587413 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4415. Min Range: -5.4415
Max Act: 5.1290. Min Act: -0.1700
Data Index: 4108986 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19