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

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

Neuron 1515 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1229673 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0225. Min Act: -0.0006

Data Index: 237772 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0220. Min Act: -0.0006

Data Index: 545191 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0212. Min Act: -0.0006

Data Index: 687150 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1267803 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0210. Min Act: -0.0006

Data Index: 58600 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0214. Min Act: -0.0006

Data Index: 7028 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1315270 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0204. Min Act: -0.0006

Data Index: 921980 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0207. Min Act: -0.0006

Data Index: 85777 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0206. Min Act: -0.0006

Data Index: 984025 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0209. Min Act: -0.0006

Data Index: 939126 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0198. Min Act: -0.0006

Data Index: 241583 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1307649 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1266429 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0200. Min Act: -0.0006

Data Index: 842043 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0205. Min Act: -0.0006

Data Index: 44701 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0194. Min Act: -0.0006

Data Index: 14460 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1098142 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0203. Min Act: -0.0006

Data Index: 553599 (C4 (Web Text))

Max Activating Token Index: 225