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

Dataset: The Pile

Neuron 4305 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1370597 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6738. Min Act: -0.0000

Data Index: 636904 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1728745 (The Pile)

Max Activating Token Index: 171

Text #3

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6658. Min Act: -0.0000

Data Index: 298969 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6634. Min Act: -0.0000

Data Index: 259474 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1749514 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1164749 (The Pile)

Max Activating Token Index: 298

Text #7

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1023478 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6353. Min Act: -0.0000

Data Index: 732260 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1586495 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6126. Min Act: -0.0000

Data Index: 34713 (The Pile)

Max Activating Token Index: 17

Text #11

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1682831 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6111. Min Act: -0.0000

Data Index: 492872 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6287. Min Act: -0.0000

Data Index: 99079 (The Pile)

Max Activating Token Index: 337

Text #14

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6234. Min Act: -0.0000

Data Index: 116425 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1481212 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6402. Min Act: -0.0000

Data Index: 252764 (The Pile)

Max Activating Token Index: 578

Text #17

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6340. Min Act: -0.0000

Data Index: 546768 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6337. Min Act: -0.0000

Data Index: 974979 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6138. Min Act: -0.0000

Data Index: 967627 (The Pile)

Max Activating Token Index: 129