Model: None
Dataset: The Pile
Neuron 1151 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.7158. Min Act: -0.1700
Data Index: 501575 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6998. Min Act: -0.1700
Data Index: 8999522 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6998. Min Act: -0.1700
Data Index: 1833605 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6838. Min Act: -0.1700
Data Index: 9278867 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6838. Min Act: -0.1700
Data Index: 372575 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6838. Min Act: -0.1700
Data Index: 4810334 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 5671745 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 519587 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 2130914 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 1123766 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 354904 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 4339562 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 4186319 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 7894258 (The Pile)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 7212191 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 2531565 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6678. Min Act: -0.1700
Data Index: 8869719 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6517. Min Act: -0.1700
Data Index: 8206210 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6517. Min Act: -0.1700
Data Index: 8739980 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7158. Min Range: -2.7158
Max Act: 2.6517. Min Act: -0.1700
Data Index: 4900765 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19