Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 430 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1639797 (Python Code)

Max Activating Token Index: 840

Text #1

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1349763 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0237. Min Act: -0.0001

Data Index: 938046 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0218. Min Act: -0.0000

Data Index: 1138453 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0209. Min Act: -0.0001

Data Index: 500569 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0215. Min Act: -0.0000

Data Index: 355943 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1563386 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0207. Min Act: -0.0001

Data Index: 468756 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1651641 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0209. Min Act: -0.0001

Data Index: 410529 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1039662 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0203. Min Act: -0.0001

Data Index: 776693 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0205. Min Act: -0.0000

Data Index: 491208 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0202. Min Act: -0.0000

Data Index: 1393366 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0202. Min Act: -0.0001

Data Index: 747318 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0199. Min Act: -0.0001

Data Index: 558777 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1410538 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1551277 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0200. Min Act: -0.0002

Data Index: 190230 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1509267 (Python Code)

Max Activating Token Index: 262