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

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

Neuron 3640 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: 0.0314. Min Range: -0.0314

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1336937 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0311. Min Act: -0.0002

Data Index: 563860 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0003

Data Index: 715556 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1189505 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1601849 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0279. Min Act: -0.0003

Data Index: 481295 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1531879 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0261. Min Act: -0.0002

Data Index: 841527 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1307882 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0227. Min Act: -0.0003

Data Index: 305921 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0258. Min Act: -0.0003

Data Index: 551127 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0253. Min Act: -0.0003

Data Index: 198638 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1510542 (Python Code)

Max Activating Token Index: 732

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1326592 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0262. Min Act: -0.0003

Data Index: 795487 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1482761 (Python Code)

Max Activating Token Index: 927

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0233. Min Act: -0.0003

Data Index: 306678 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0245. Min Act: -0.0003

Data Index: 216285 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0253. Min Act: -0.0003

Data Index: 4843 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1580728 (Python Code)

Max Activating Token Index: 158