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

Dataset: The Pile

Neuron 3063 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: 0.2360. Min Range: -0.2360

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1032800 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1312772 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2189. Min Act: -0.0000

Data Index: 84280 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1896. Min Act: -0.0000

Data Index: 746722 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1807. Min Act: -0.0000

Data Index: 44491 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1213671 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1455320 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1720. Min Act: -0.0000

Data Index: 21943 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1561658 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1665. Min Act: -0.0000

Data Index: 101017 (The Pile)

Max Activating Token Index: 891

Text #10

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1640. Min Act: -0.0000

Data Index: 493370 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1565. Min Act: -0.0000

Data Index: 821606 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1932858 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1945129 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1971173 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1642. Min Act: -0.0000

Data Index: 35448 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1408. Min Act: -0.0000

Data Index: 545626 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1377162 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1304. Min Act: -0.0000

Data Index: 552730 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1593. Min Act: -0.0000

Data Index: 613862 (The Pile)

Max Activating Token Index: 853