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

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

Neuron 2718 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0002

Data Index: 250489 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0300. Min Act: -0.0002

Data Index: 514399 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0264. Min Act: -0.0002

Data Index: 840137 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0238. Min Act: -0.0002

Data Index: 574101 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0231. Min Act: -0.0002

Data Index: 285708 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0215. Min Act: -0.0002

Data Index: 252105 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1334929 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1046969 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0204. Min Act: -0.0002

Data Index: 222910 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0169. Min Act: -0.0002

Data Index: 980839 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0198. Min Act: -0.0002

Data Index: 757341 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0206. Min Act: -0.0002

Data Index: 726785 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0193. Min Act: -0.0002

Data Index: 114649 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0197. Min Act: -0.0002

Data Index: 398542 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1152986 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0197. Min Act: -0.0002

Data Index: 991448 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0194. Min Act: -0.0003

Data Index: 350372 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0198. Min Act: -0.0002

Data Index: 408362 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0193. Min Act: -0.0002

Data Index: 993664 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1483544 (Python Code)

Max Activating Token Index: 109