Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 446 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3831. Min Act: -0.1700
Data Index: 8823609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3831. Min Act: -0.1700
Data Index: 2177429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3831. Min Act: -0.1700
Data Index: 5696426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3517. Min Act: -0.1700
Data Index: 8753900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3517. Min Act: -0.1700
Data Index: 2797773 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3517. Min Act: -0.1700
Data Index: 6237651 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3517. Min Act: -0.1700
Data Index: 6125443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 7155816 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 1645528 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 6707731 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 70901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 179793 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 5896340 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 5635158 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 5490827 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 4192160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.2890. Min Act: -0.1700
Data Index: 3961346 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 3186392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 630094 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3831. Min Range: -3.3831
Max Act: 3.3204. Min Act: -0.1700
Data Index: 2045133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19