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

Dataset: The Pile

Neuron 747 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: 4.0802. Min Range: -4.0802

Max Act: 4.0802. Min Act: -0.0000

Data Index: 1853689 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.9918. Min Act: -0.0000

Data Index: 1943643 (The Pile)

Max Activating Token Index: 357

Text #2

Max Range: 4.0802. Min Range: -4.0802

Max Act: 4.0704. Min Act: -0.0000

Data Index: 563023 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.9025. Min Act: -0.0000

Data Index: 1470206 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.8658. Min Act: -0.0000

Data Index: 1224032 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.8234. Min Act: -0.0000

Data Index: 1251560 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.8171. Min Act: -0.0000

Data Index: 1246292 (The Pile)

Max Activating Token Index: 931

Text #7

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.8950. Min Act: -0.0000

Data Index: 1567431 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.8614. Min Act: -0.0000

Data Index: 1390140 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.9771. Min Act: -0.0000

Data Index: 1068863 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.4715. Min Act: -0.0000

Data Index: 1838763 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.8962. Min Act: -0.0000

Data Index: 1300668 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.7227. Min Act: -0.0000

Data Index: 822592 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.5467. Min Act: -0.0000

Data Index: 1231760 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.5506. Min Act: -0.0000

Data Index: 625537 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.3690. Min Act: -0.0000

Data Index: 912545 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.4428. Min Act: -0.0000

Data Index: 1163799 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.2865. Min Act: -0.0000

Data Index: 641250 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.0190. Min Act: -0.0000

Data Index: 1169900 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 4.0802. Min Range: -4.0802

Max Act: 3.4267. Min Act: -0.0000

Data Index: 1792508 (The Pile)

Max Activating Token Index: 1002