Model: None
Dataset: The Pile
Neuron 830 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6718. Min Act: -0.1700
Data Index: 7388732 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6718. Min Act: -0.1700
Data Index: 3099804 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6561. Min Act: -0.1700
Data Index: 1863156 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6561. Min Act: -0.1700
Data Index: 1989300 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 4592913 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 767385 (The Pile)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 8154591 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 27951 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 3900716 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 9825127 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 3892237 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6248. Min Act: -0.1700
Data Index: 968435 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6248. Min Act: -0.1700
Data Index: 1775573 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6248. Min Act: -0.1700
Data Index: 1110255 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6248. Min Act: -0.1700
Data Index: 2365073 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6248. Min Act: -0.1700
Data Index: 9597692 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6248. Min Act: -0.1700
Data Index: 5462151 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6248. Min Act: -0.1700
Data Index: 3379436 (The Pile)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6092. Min Act: -0.1700
Data Index: 6369432 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6092. Min Act: -0.1700
Data Index: 7238637 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19