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

Dataset: The Pile

Neuron 3307 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: 0.5833. Min Range: -0.5833

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1179510 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1289655 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1337967 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1391097 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4899. Min Act: -0.0000

Data Index: 233044 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5833. Min Act: -0.0000

Data Index: 999715 (The Pile)

Max Activating Token Index: 902

Text #6

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4623. Min Act: -0.0000

Data Index: 424240 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1561355 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4482. Min Act: -0.0000

Data Index: 477462 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1304116 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4045. Min Act: -0.0000

Data Index: 32708 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4399. Min Act: -0.0000

Data Index: 803547 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1188101 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1712314 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4204. Min Act: -0.0000

Data Index: 853991 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3905. Min Act: -0.0000

Data Index: 83830 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4413. Min Act: -0.0000

Data Index: 242251 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1224940 (The Pile)

Max Activating Token Index: 230

Text #18

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1952024 (The Pile)

Max Activating Token Index: 960

Text #19

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1927213 (The Pile)

Max Activating Token Index: 184