Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1428 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1429127 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1044649 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1998. Min Act: -0.0000

Data Index: 569649 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1694426 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1344317 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1672553 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1660. Min Act: -0.0000

Data Index: 645810 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1711. Min Act: -0.0000

Data Index: 206629 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1966. Min Act: -0.0000

Data Index: 585759 (The Pile)

Max Activating Token Index: 986

Text #9

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1623. Min Act: -0.0000

Data Index: 744493 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1810383 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1658. Min Act: -0.0000

Data Index: 564058 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1505. Min Act: -0.0000

Data Index: 62311 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1519. Min Act: -0.0000

Data Index: 879113 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1138693 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1625. Min Act: -0.0000

Data Index: 436230 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1563. Min Act: -0.0000

Data Index: 986757 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1557. Min Act: -0.0000

Data Index: 115438 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1036533 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1673. Min Act: -0.0000

Data Index: 470950 (The Pile)

Max Activating Token Index: 219