Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1469 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0003

Data Index: 1079316 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1499. Min Act: -0.0003

Data Index: 400301 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1544. Min Act: -0.0003

Data Index: 959688 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1390. Min Act: -0.0003

Data Index: 25149 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1390. Min Act: -0.0003

Data Index: 677336 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1390. Min Act: -0.0003

Data Index: 1121805 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1371. Min Act: -0.0003

Data Index: 546697 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1365. Min Act: -0.0003

Data Index: 1053746 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1360. Min Act: -0.0003

Data Index: 1109503 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1344. Min Act: -0.0003

Data Index: 767265 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1316108 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1290. Min Act: -0.0003

Data Index: 467986 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1274. Min Act: -0.0003

Data Index: 1010814 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1260. Min Act: -0.0003

Data Index: 233519 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1256. Min Act: -0.0003

Data Index: 999422 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1248. Min Act: -0.0003

Data Index: 250961 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1232. Min Act: -0.0003

Data Index: 1328898 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1238. Min Act: -0.0003

Data Index: 350031 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1185. Min Act: -0.0003

Data Index: 316141 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1177. Min Act: -0.0003

Data Index: 972653 (C4 (Web Text))

Max Activating Token Index: 150