Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2271 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2755. Min Act: -0.0000

Data Index: 425578 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1740248 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2674. Min Act: 0.0000

Data Index: 1775753 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2633. Min Act: -0.0000

Data Index: 80434 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1174972 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1153777 (The Pile)

Max Activating Token Index: 924

Text #6

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1699693 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2318. Min Act: -0.0001

Data Index: 227988 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1772437 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2370. Min Act: 0.0000

Data Index: 1532062 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1957271 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2242. Min Act: -0.0000

Data Index: 766131 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2231. Min Act: -0.0000

Data Index: 284259 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2228. Min Act: -0.0000

Data Index: 304107 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1565080 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1860754 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1669783 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1455431 (The Pile)

Max Activating Token Index: 218

Text #18

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1507960 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2140. Min Act: 0.0000

Data Index: 1516263 (The Pile)

Max Activating Token Index: 65