Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5366 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0002

Data Index: 183543 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0322. Min Act: -0.0002

Data Index: 78082 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0307. Min Act: -0.0002

Data Index: 365353 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1044886 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0298. Min Act: -0.0002

Data Index: 574465 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0274. Min Act: -0.0002

Data Index: 512664 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0281. Min Act: -0.0002

Data Index: 626722 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0274. Min Act: -0.0002

Data Index: 827500 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0275. Min Act: -0.0002

Data Index: 206152 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0263. Min Act: -0.0002

Data Index: 743925 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0266. Min Act: -0.0002

Data Index: 973252 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0268. Min Act: -0.0002

Data Index: 879484 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0261. Min Act: -0.0002

Data Index: 499360 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0268. Min Act: -0.0002

Data Index: 358701 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0263. Min Act: -0.0002

Data Index: 928051 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1053855 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0260. Min Act: -0.0002

Data Index: 10419 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0259. Min Act: -0.0002

Data Index: 882660 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1052954 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1193159 (C4 (Web Text))

Max Activating Token Index: 418