Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.6036. Min Act: -0.1700
Data Index: 2901225 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.6036. Min Act: -0.1700
Data Index: 3170123 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.6036. Min Act: -0.1700
Data Index: 3890385 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.6036. Min Act: -0.1700
Data Index: 4271804 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5723. Min Act: -0.1700
Data Index: 4878997 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5723. Min Act: -0.1700
Data Index: 7554121 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5723. Min Act: -0.1700
Data Index: 910585 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5410. Min Act: -0.1700
Data Index: 6593738 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5410. Min Act: -0.1700
Data Index: 53947 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5410. Min Act: -0.1700
Data Index: 1576933 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5410. Min Act: -0.1700
Data Index: 6768498 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5410. Min Act: -0.1700
Data Index: 801740 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5410. Min Act: -0.1700
Data Index: 4878996 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5723. Min Act: -0.1700
Data Index: 8166002 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5410. Min Act: -0.1700
Data Index: 1600710 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5723. Min Act: -0.1700
Data Index: 5484894 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5097. Min Act: -0.1700
Data Index: 67251 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5097. Min Act: -0.1700
Data Index: 5457522 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.5097. Min Act: -0.1700
Data Index: 2489199 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6036. Min Range: -3.6036
Max Act: 3.4784. Min Act: -0.1700
Data Index: 5698388 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19