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

Dataset: The Pile

Neuron 4906 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1602277 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3248. Min Act: -0.0000

Data Index: 146785 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1195807 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1627868 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1930. Min Act: -0.0000

Data Index: 835247 (The Pile)

Max Activating Token Index: 840

Text #5

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1728897 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1730485 (The Pile)

Max Activating Token Index: 725

Text #7

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1870953 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1572. Min Act: -0.0000

Data Index: 477012 (The Pile)

Max Activating Token Index: 423

Text #9

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1182602 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1676. Min Act: -0.0000

Data Index: 100010 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1127284 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1678. Min Act: -0.0000

Data Index: 605807 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1774597 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1368. Min Act: -0.0000

Data Index: 54511 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1441. Min Act: -0.0000

Data Index: 975085 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1933. Min Act: -0.0000

Data Index: 795342 (The Pile)

Max Activating Token Index: 316

Text #17

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1772. Min Act: -0.0000

Data Index: 440699 (The Pile)

Max Activating Token Index: 66

Text #18

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1793. Min Act: -0.0000

Data Index: 943204 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.1459. Min Act: -0.0000

Data Index: 25228 (The Pile)

Max Activating Token Index: 881