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

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

Neuron 1624 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 819152 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0310. Min Act: -0.0003

Data Index: 809461 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1155080 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0286. Min Act: -0.0003

Data Index: 453567 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1239799 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0234. Min Act: -0.0003

Data Index: 451272 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0229. Min Act: -0.0002

Data Index: 537800 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0220. Min Act: -0.0002

Data Index: 146393 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0219. Min Act: -0.0002

Data Index: 942448 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0214. Min Act: -0.0002

Data Index: 786091 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1228908 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0215. Min Act: -0.0002

Data Index: 989650 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1288334 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0213. Min Act: -0.0002

Data Index: 643901 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0207. Min Act: -0.0002

Data Index: 407075 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1268706 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0200. Min Act: -0.0002

Data Index: 160796 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0203. Min Act: -0.0002

Data Index: 644578 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1263424 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0197. Min Act: -0.0003

Data Index: 94289 (C4 (Web Text))

Max Activating Token Index: 159