Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 510 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0264. Min Act: -0.0006

Data Index: 666482 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0302. Min Act: -0.0006

Data Index: 36877 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0283. Min Act: -0.0006

Data Index: 512724 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0283. Min Act: -0.0006

Data Index: 72614 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1213005 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0243. Min Act: -0.0006

Data Index: 647144 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0275. Min Act: -0.0006

Data Index: 1055194 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0226. Min Act: -0.0006

Data Index: 861365 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1134848 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0236. Min Act: -0.0006

Data Index: 149825 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0237. Min Act: -0.0006

Data Index: 5396 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0240. Min Act: -0.0006

Data Index: 645189 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1179844 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0230. Min Act: -0.0006

Data Index: 93382 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0225. Min Act: -0.0006

Data Index: 309016 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0208. Min Act: -0.0006

Data Index: 147309 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0234. Min Act: -0.0006

Data Index: 593413 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0205. Min Act: -0.0006

Data Index: 709605 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0223. Min Act: -0.0006

Data Index: 958458 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0244. Min Act: -0.0006

Data Index: 364632 (C4 (Web Text))

Max Activating Token Index: 436