Model: None
Dataset: The Pile
Neuron 830 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.8866. Min Act: -0.1700
Data Index: 2742444 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.7752. Min Act: -0.1699
Data Index: 5177619 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.7433. Min Act: -0.1700
Data Index: 10161587 (The Pile)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.7273. Min Act: -0.1700
Data Index: 1643111 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.7113. Min Act: -0.1700
Data Index: 4348114 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.6793. Min Act: -0.1700
Data Index: 283438 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.6793. Min Act: -0.1700
Data Index: 6703637 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.6312. Min Act: -0.1700
Data Index: 1383914 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5991. Min Act: -0.1700
Data Index: 1437337 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5991. Min Act: -0.1700
Data Index: 455994 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5830. Min Act: -0.1700
Data Index: 8427866 (The Pile)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5830. Min Act: -0.1700
Data Index: 7451203 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5830. Min Act: -0.1700
Data Index: 4185715 (The Pile)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5830. Min Act: -0.1700
Data Index: 299392 (The Pile)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5668. Min Act: -0.1700
Data Index: 666155 (The Pile)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5991. Min Act: -0.1700
Data Index: 8186081 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5346. Min Act: -0.1700
Data Index: 2436843 (The Pile)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5346. Min Act: -0.1700
Data Index: 7070867 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5507. Min Act: -0.1700
Data Index: 9214929 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8866. Min Range: -2.8866
Max Act: 2.5346. Min Act: -0.1700
Data Index: 8622618 (The Pile)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19