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

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

Neuron 2889 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: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0004

Data Index: 322442 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1173015 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0306. Min Act: -0.0004

Data Index: 291774 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0277. Min Act: -0.0004

Data Index: 593330 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0274. Min Act: -0.0004

Data Index: 41791 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0268. Min Act: -0.0004

Data Index: 1204012 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0263. Min Act: -0.0004

Data Index: 721598 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0260. Min Act: -0.0004

Data Index: 630360 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0260. Min Act: -0.0004

Data Index: 1206182 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0259. Min Act: -0.0004

Data Index: 1022963 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0218. Min Act: -0.0004

Data Index: 856651 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0249. Min Act: -0.0004

Data Index: 191819 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0257. Min Act: -0.0004

Data Index: 740425 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0227. Min Act: -0.0004

Data Index: 949575 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0237. Min Act: -0.0004

Data Index: 45755 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0248. Min Act: -0.0004

Data Index: 184509 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0243. Min Act: -0.0004

Data Index: 457781 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0244. Min Act: -0.0004

Data Index: 386103 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0238. Min Act: -0.0004

Data Index: 48263 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0233. Min Act: -0.0004

Data Index: 290671 (C4 (Web Text))

Max Activating Token Index: 253