Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 401 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1150454 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1948. Min Act: -0.0000

Data Index: 909142 (The Pile)

Max Activating Token Index: 233

Text #2

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1762. Min Act: -0.0000

Data Index: 936885 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1903965 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1202017 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1796. Min Act: -0.0000

Data Index: 851079 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1578. Min Act: -0.0000

Data Index: 145489 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1991289 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1135043 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1687. Min Act: -0.0000

Data Index: 555138 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1558. Min Act: -0.0000

Data Index: 308051 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1562. Min Act: -0.0000

Data Index: 311347 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1509614 (The Pile)

Max Activating Token Index: 271

Text #13

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1488. Min Act: -0.0000

Data Index: 566005 (The Pile)

Max Activating Token Index: 29

Text #14

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1614. Min Act: -0.0000

Data Index: 613473 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1571. Min Act: -0.0000

Data Index: 836193 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1560. Min Act: -0.0000

Data Index: 155971 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1789045 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1749566 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1589. Min Act: -0.0000

Data Index: 902717 (The Pile)

Max Activating Token Index: 71