Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 785 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.7666. Min Act: -0.0000
Data Index: 66138 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.5228. Min Act: -0.0000
Data Index: 513820 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.2472. Min Act: 0.0000
Data Index: 808497 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.2307. Min Act: -0.0000
Data Index: 1661523 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.0587. Min Act: -0.0000
Data Index: 264164 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.1243. Min Act: -0.0000
Data Index: 1854596 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.0506. Min Act: 0.0000
Data Index: 1415238 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.1257. Min Act: 0.0000
Data Index: 1931555 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.1056. Min Act: 0.0000
Data Index: 1640971 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7666. Min Range: -2.7666
Max Act: 1.9790. Min Act: -0.0000
Data Index: 340744 (The Pile)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.0834. Min Act: -0.0000
Data Index: 1227592 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.1569. Min Act: -0.0000
Data Index: 1752515 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.0793. Min Act: -0.0000
Data Index: 38132 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7666. Min Range: -2.7666
Max Act: 1.8412. Min Act: 0.0000
Data Index: 1619780 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7666. Min Range: -2.7666
Max Act: 1.9358. Min Act: 0.0000
Data Index: 765296 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.0499. Min Act: 0.0000
Data Index: 536388 (The Pile)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7666. Min Range: -2.7666
Max Act: 1.9159. Min Act: 0.0000
Data Index: 887925 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7666. Min Range: -2.7666
Max Act: 1.8794. Min Act: 0.0000
Data Index: 1627766 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7666. Min Range: -2.7666
Max Act: 1.9279. Min Act: -0.0000
Data Index: 944457 (The Pile)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7666. Min Range: -2.7666
Max Act: 2.0493. Min Act: -0.0000
Data Index: 1505307 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19