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

Dataset: The Pile

Neuron 4497 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: 1.3364. Min Range: -1.3364

Max Act: 1.3364. Min Act: -0.0000

Data Index: 1234347 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0517. Min Act: -0.0000

Data Index: 1660482 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9636. Min Act: -0.0000

Data Index: 518485 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1015333 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9617. Min Act: -0.0000

Data Index: 454259 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9099. Min Act: -0.0000

Data Index: 777593 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9437. Min Act: -0.0000

Data Index: 139210 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1128210 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1646087 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1999686 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8995. Min Act: -0.0000

Data Index: 166612 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1932379 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9520. Min Act: -0.0000

Data Index: 75187 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8666. Min Act: -0.0000

Data Index: 527917 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8886. Min Act: -0.0000

Data Index: 519327 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1316780 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1520159 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9005. Min Act: -0.0000

Data Index: 125569 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1147964 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8965. Min Act: -0.0000

Data Index: 875030 (The Pile)

Max Activating Token Index: 850