Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 227 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.4218. Min Act: -0.0001
Data Index: 97109 (The Pile)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.4247. Min Act: -0.0001
Data Index: 409518 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.4558. Min Act: -0.0001
Data Index: 46784 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.2856. Min Act: -0.0001
Data Index: 609714 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.3259. Min Act: -0.0001
Data Index: 1490803 (The Pile)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.4778. Min Act: -0.0001
Data Index: 1257420 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.1971. Min Act: -0.0001
Data Index: 2727 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.1822. Min Act: -0.0001
Data Index: 897443 (The Pile)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.2658. Min Act: -0.0001
Data Index: 1553086 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.2504. Min Act: -0.0001
Data Index: 1746376 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.2034. Min Act: -0.0001
Data Index: 630534 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.2783. Min Act: -0.0001
Data Index: 1572103 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.1408. Min Act: -0.0001
Data Index: 1686922 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.2906. Min Act: -0.0001
Data Index: 1191687 (The Pile)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.1812. Min Act: -0.0001
Data Index: 68914 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.0599. Min Act: -0.0001
Data Index: 268363 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.2021. Min Act: -0.0001
Data Index: 125107 (The Pile)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.1867. Min Act: -0.0001
Data Index: 1045822 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.2733. Min Act: -0.0001
Data Index: 1056950 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4778. Min Range: -1.4778
Max Act: 1.1401. Min Act: -0.0001
Data Index: 1804664 (The Pile)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19