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

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

Neuron 2604 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0003

Data Index: 272601 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0314. Min Act: -0.0003

Data Index: 33824 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0292. Min Act: -0.0003

Data Index: 741922 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0269. Min Act: -0.0003

Data Index: 185526 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0254. Min Act: -0.0003

Data Index: 944511 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0255. Min Act: -0.0003

Data Index: 353686 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0257. Min Act: -0.0003

Data Index: 859438 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1012499 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0238. Min Act: -0.0003

Data Index: 888749 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0241. Min Act: -0.0003

Data Index: 780421 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0245. Min Act: -0.0003

Data Index: 622361 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0249. Min Act: -0.0003

Data Index: 632492 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1028396 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0236. Min Act: -0.0003

Data Index: 774943 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1274327 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0217. Min Act: -0.0003

Data Index: 951776 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1281325 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0219. Min Act: -0.0003

Data Index: 278218 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1199034 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1307805 (C4 (Web Text))

Max Activating Token Index: 58