Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1645 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1820. Min Act: -0.0001
Data Index: 1843737 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1817. Min Act: -0.0001
Data Index: 657797 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1809. Min Act: -0.0001
Data Index: 513930 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1726. Min Act: -0.0001
Data Index: 786003 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1717. Min Act: -0.0001
Data Index: 332787 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1702. Min Act: -0.0001
Data Index: 1181504 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1748. Min Act: -0.0001
Data Index: 1032596 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1641. Min Act: -0.0001
Data Index: 1261832 (The Pile)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1715. Min Act: -0.0001
Data Index: 1154659 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1654. Min Act: -0.0001
Data Index: 91772 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1585. Min Act: -0.0001
Data Index: 945873 (The Pile)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1577. Min Act: -0.0001
Data Index: 1237737 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1638. Min Act: -0.0001
Data Index: 1457724 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1635. Min Act: -0.0001
Data Index: 1624070 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1584. Min Act: -0.0001
Data Index: 340291 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1707. Min Act: -0.0001
Data Index: 1479170 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1585. Min Act: -0.0001
Data Index: 1077131 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1637. Min Act: -0.0001
Data Index: 644633 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1578. Min Act: -0.0001
Data Index: 1848609 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1820. Min Range: -0.1820
Max Act: 0.1529. Min Act: -0.0001
Data Index: 464668 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19