Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 8 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0001

Data Index: 996132 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0416. Min Act: -0.0001

Data Index: 749066 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1118763 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0345. Min Act: -0.0004

Data Index: 87154 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1281526 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0329. Min Act: -0.0002

Data Index: 717252 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0328. Min Act: -0.0003

Data Index: 416277 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0306. Min Act: -0.0003

Data Index: 394915 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0313. Min Act: -0.0003

Data Index: 114999 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0315. Min Act: -0.0003

Data Index: 778927 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0309. Min Act: -0.0004

Data Index: 223208 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0304. Min Act: -0.0003

Data Index: 976227 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0299. Min Act: -0.0003

Data Index: 480516 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0292. Min Act: -0.0001

Data Index: 437867 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1330328 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0289. Min Act: -0.0003

Data Index: 385122 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0288. Min Act: -0.0003

Data Index: 996613 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0297. Min Act: -0.0004

Data Index: 348622 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0288. Min Act: -0.0003

Data Index: 867332 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0292. Min Act: -0.0002

Data Index: 424341 (C4 (Web Text))

Max Activating Token Index: 350