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

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

Neuron 3601 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0001

Data Index: 343657 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1238594 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0203. Min Act: -0.0001

Data Index: 624747 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0224. Min Act: -0.0001

Data Index: 529729 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1458058 (Python Code)

Max Activating Token Index: 707

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0205. Min Act: -0.0001

Data Index: 504436 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0204. Min Act: -0.0001

Data Index: 458441 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0179. Min Act: -0.0001

Data Index: 128318 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0202. Min Act: -0.0001

Data Index: 629643 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0199. Min Act: -0.0001

Data Index: 110050 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0186. Min Act: -0.0001

Data Index: 412552 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1620243 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1209300 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0180. Min Act: -0.0001

Data Index: 1645218 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0219. Min Act: -0.0001

Data Index: 907820 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0179. Min Act: -0.0001

Data Index: 1553735 (Python Code)

Max Activating Token Index: 667

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0184. Min Act: -0.0001

Data Index: 961114 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0189. Min Act: -0.0001

Data Index: 782527 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0167. Min Act: -0.0001

Data Index: 441531 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0163. Min Act: -0.0001

Data Index: 826999 (C4 (Web Text))

Max Activating Token Index: 948