Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4192 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.7535. Min Act: -0.1700
Data Index: 804314 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.7223. Min Act: -0.1700
Data Index: 7803002 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.6285. Min Act: -0.1700
Data Index: 1999606 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.6285. Min Act: -0.1700
Data Index: 8337053 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5660. Min Act: -0.1700
Data Index: 1620028 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5660. Min Act: -0.1700
Data Index: 4447323 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5035. Min Act: -0.1700
Data Index: 5790098 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5035. Min Act: -0.1700
Data Index: 890761 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4723. Min Act: -0.1700
Data Index: 3848780 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4723. Min Act: -0.1700
Data Index: 3569393 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4723. Min Act: -0.1700
Data Index: 6840515 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4410. Min Act: -0.1700
Data Index: 3280452 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4410. Min Act: -0.1700
Data Index: 1232198 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4410. Min Act: -0.1700
Data Index: 5699336 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.3785. Min Act: -0.1700
Data Index: 8559143 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.3785. Min Act: -0.1700
Data Index: 5416633 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4098. Min Act: -0.1700
Data Index: 2872676 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.3785. Min Act: -0.1700
Data Index: 5394696 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.3160. Min Act: -0.1700
Data Index: 5242629 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.2848. Min Act: -0.1700
Data Index: 7607978 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19