Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 534 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0004

Data Index: 309110 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0258. Min Act: -0.0004

Data Index: 907302 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0226. Min Act: -0.0004

Data Index: 1091611 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0222. Min Act: -0.0004

Data Index: 833046 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0208. Min Act: -0.0004

Data Index: 1304611 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0211. Min Act: -0.0004

Data Index: 385539 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0214. Min Act: -0.0004

Data Index: 336076 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0200. Min Act: -0.0004

Data Index: 673256 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0207. Min Act: -0.0004

Data Index: 1100223 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0183. Min Act: -0.0004

Data Index: 108312 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0204. Min Act: -0.0004

Data Index: 1126642 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0197. Min Act: -0.0004

Data Index: 1012634 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0196. Min Act: -0.0004

Data Index: 69823 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0175. Min Act: -0.0004

Data Index: 426787 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0203. Min Act: -0.0004

Data Index: 400361 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0195. Min Act: -0.0004

Data Index: 1223389 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0184. Min Act: -0.0004

Data Index: 1223311 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0187. Min Act: -0.0004

Data Index: 350867 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0180. Min Act: -0.0004

Data Index: 164695 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0182. Min Act: -0.0004

Data Index: 192346 (C4 (Web Text))

Max Activating Token Index: 77