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

Dataset: The Pile

Neuron 4765 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: 1.1882. Min Range: -1.1882

Max Act: 1.1882. Min Act: -0.0000

Data Index: 319891 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1865244 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1108321 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.0717. Min Act: -0.0000

Data Index: 835751 (The Pile)

Max Activating Token Index: 910

Text #4

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1726797 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1219142 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1187303 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8602. Min Act: -0.0000

Data Index: 828657 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1718026 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1441111 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1101410 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7925. Min Act: -0.0000

Data Index: 541498 (The Pile)

Max Activating Token Index: 656

Text #12

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1878454 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1668170 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1094959 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1361725 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1701027 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1057139 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.6207. Min Act: -0.0000

Data Index: 391723 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.6084. Min Act: -0.0000

Data Index: 173415 (The Pile)

Max Activating Token Index: 760