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

Dataset: The Pile

Neuron 2636 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1205206 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6741. Min Act: -0.0000

Data Index: 171897 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7400. Min Act: -0.0000

Data Index: 788139 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5870. Min Act: -0.0000

Data Index: 668893 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1950759 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6325. Min Act: -0.0000

Data Index: 468197 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5935. Min Act: -0.0000

Data Index: 277515 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1559282 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5722. Min Act: -0.0000

Data Index: 1294167 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5902. Min Act: -0.0000

Data Index: 603735 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5691. Min Act: -0.0000

Data Index: 73343 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5191. Min Act: -0.0000

Data Index: 738187 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1299482 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1631862 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1434460 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1173855 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5112. Min Act: -0.0000

Data Index: 515553 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1522348 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5384. Min Act: -0.0000

Data Index: 409060 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1695935 (The Pile)

Max Activating Token Index: 27