Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.3469. Min Act: -0.1700
Data Index: 4075517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.3305. Min Act: -0.1700
Data Index: 4580820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2976. Min Act: -0.1700
Data Index: 6202614 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2976. Min Act: -0.1700
Data Index: 6829915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2812. Min Act: -0.1700
Data Index: 3895295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2812. Min Act: -0.1700
Data Index: 7499695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2812. Min Act: -0.1700
Data Index: 7431500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2812. Min Act: -0.1700
Data Index: 6469230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2812. Min Act: -0.1700
Data Index: 4168062 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2812. Min Act: -0.1700
Data Index: 7012441 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2647. Min Act: -0.1700
Data Index: 7667536 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2647. Min Act: -0.1700
Data Index: 6718936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2482. Min Act: -0.1700
Data Index: 3970744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2482. Min Act: -0.1700
Data Index: 1111536 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2482. Min Act: -0.1700
Data Index: 5808195 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2316. Min Act: -0.1700
Data Index: 7886853 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2482. Min Act: -0.1700
Data Index: 7364456 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2316. Min Act: -0.1700
Data Index: 7019321 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2151. Min Act: -0.1700
Data Index: 6209095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3469. Min Range: -2.3469
Max Act: 2.2316. Min Act: -0.1700
Data Index: 8636683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19