Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4536. Min Act: -0.1700
Data Index: 8140715 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4536. Min Act: -0.1700
Data Index: 284982 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4379. Min Act: -0.1700
Data Index: 1234483 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4379. Min Act: -0.1700
Data Index: 6158516 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4379. Min Act: -0.1700
Data Index: 4201627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4222. Min Act: -0.1700
Data Index: 2795300 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4222. Min Act: -0.1700
Data Index: 169392 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4379. Min Act: -0.1700
Data Index: 3509445 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4222. Min Act: -0.1700
Data Index: 4592374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4222. Min Act: -0.1700
Data Index: 899688 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4222. Min Act: -0.1700
Data Index: 6685618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4066. Min Act: -0.1700
Data Index: 2782874 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4066. Min Act: -0.1700
Data Index: 2223853 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4066. Min Act: -0.1700
Data Index: 8294898 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4066. Min Act: -0.1700
Data Index: 8224174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4066. Min Act: -0.1700
Data Index: 4178009 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4066. Min Act: -0.1700
Data Index: 3623525 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.4066. Min Act: -0.1700
Data Index: 4758357 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.3909. Min Act: -0.1700
Data Index: 3694138 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4536. Min Range: -3.4536
Max Act: 3.3909. Min Act: -0.1700
Data Index: 8003034 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19