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

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

Neuron 1639 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: 0.0317. Min Range: -0.0317

Max Act: 0.0311. Min Act: -0.0003

Data Index: 929018 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0003

Data Index: 855048 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0294. Min Act: -0.0002

Data Index: 718441 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0282. Min Act: -0.0003

Data Index: 48343 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0282. Min Act: -0.0003

Data Index: 595180 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1262599 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0233. Min Act: -0.0002

Data Index: 521951 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0237. Min Act: -0.0003

Data Index: 515924 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1251880 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0239. Min Act: -0.0003

Data Index: 686979 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0225. Min Act: -0.0003

Data Index: 403 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1287326 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0231. Min Act: -0.0003

Data Index: 905540 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0232. Min Act: -0.0003

Data Index: 863546 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1072490 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0231. Min Act: -0.0003

Data Index: 911886 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0230. Min Act: -0.0002

Data Index: 287068 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0224. Min Act: -0.0003

Data Index: 900135 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1083383 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0227. Min Act: -0.0003

Data Index: 48630 (C4 (Web Text))

Max Activating Token Index: 375