Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2634 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.8990. Min Act: -0.1700
Data Index: 1056039 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.8990. Min Act: -0.1700
Data Index: 5660302 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.8365. Min Act: -0.1700
Data Index: 8097072 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.8053. Min Act: -0.1700
Data Index: 8560198 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.8053. Min Act: -0.1700
Data Index: 3128684 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7740. Min Act: -0.1700
Data Index: 2890822 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7740. Min Act: -0.1700
Data Index: 6968412 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7740. Min Act: -0.1700
Data Index: 2254011 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7740. Min Act: -0.1700
Data Index: 1257484 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7740. Min Act: -0.1700
Data Index: 4260640 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7428. Min Act: -0.1700
Data Index: 1562099 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7115. Min Act: -0.1700
Data Index: 7221909 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7428. Min Act: -0.1700
Data Index: 443983 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7115. Min Act: -0.1700
Data Index: 1483754 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.7115. Min Act: -0.1700
Data Index: 6413276 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.6803. Min Act: -0.1700
Data Index: 3385909 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.6803. Min Act: -0.1700
Data Index: 1803802 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.6803. Min Act: -0.1700
Data Index: 4879287 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.6803. Min Act: -0.1700
Data Index: 6903983 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8990. Min Range: -4.8990
Max Act: 4.6490. Min Act: -0.1700
Data Index: 5751337 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19