Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3272 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0306. Min Act: -0.0003

Data Index: 78799 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0323. Min Act: -0.0003

Data Index: 402324 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0340. Min Act: -0.0003

Data Index: 343971 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0274. Min Act: -0.0002

Data Index: 498111 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0267. Min Act: -0.0003

Data Index: 892003 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0270. Min Act: -0.0003

Data Index: 367495 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0262. Min Act: -0.0003

Data Index: 66227 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0237. Min Act: -0.0002

Data Index: 885633 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0261. Min Act: -0.0003

Data Index: 635896 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1170786 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0255. Min Act: -0.0003

Data Index: 138724 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1026392 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0260. Min Act: -0.0003

Data Index: 992480 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0256. Min Act: -0.0003

Data Index: 442046 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0250. Min Act: -0.0003

Data Index: 318098 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1292409 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0209. Min Act: -0.0003

Data Index: 726924 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0217. Min Act: -0.0003

Data Index: 398554 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0245. Min Act: -0.0003

Data Index: 13213 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0239. Min Act: -0.0003

Data Index: 796090 (C4 (Web Text))

Max Activating Token Index: 349