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

Dataset: The Pile

Neuron 1471 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.7327. Min Act: -0.0000

Data Index: 598881 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.4968. Min Act: -0.0000

Data Index: 630430 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1679032 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.2266. Min Act: -0.0000

Data Index: 13979 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1828516 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.1247. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 811

Text #6

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1888153 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.2446. Min Act: -0.0000

Data Index: 1909916 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1979982 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.0748. Min Act: -0.0000

Data Index: 130195 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1851328 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.2437. Min Act: -0.0000

Data Index: 540362 (The Pile)

Max Activating Token Index: 827

Text #12

Max Range: 1.7327. Min Range: -1.7327

Max Act: 0.9676. Min Act: -0.0000

Data Index: 335507 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.1754. Min Act: -0.0000

Data Index: 1269625 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.0623. Min Act: -0.0000

Data Index: 942735 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 1.7327. Min Range: -1.7327

Max Act: 0.9573. Min Act: -0.0000

Data Index: 330581 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 1.7327. Min Range: -1.7327

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1556395 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.0088. Min Act: -0.0000

Data Index: 463480 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.0061. Min Act: -0.0000

Data Index: 675816 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 1.7327. Min Range: -1.7327

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1340884 (The Pile)

Max Activating Token Index: 306