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

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

Neuron 4850 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: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0002

Data Index: 984414 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0381. Min Act: -0.0002

Data Index: 612205 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0339. Min Act: -0.0002

Data Index: 403089 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0291. Min Act: -0.0002

Data Index: 34645 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1328487 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1339199 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1114015 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0327. Min Act: -0.0003

Data Index: 472685 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0298. Min Act: -0.0002

Data Index: 95410 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0261. Min Act: -0.0002

Data Index: 313667 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1299813 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0304. Min Act: -0.0002

Data Index: 800166 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0285. Min Act: -0.0002

Data Index: 766784 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0299. Min Act: -0.0002

Data Index: 309314 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0289. Min Act: -0.0002

Data Index: 633610 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1011152 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0282. Min Act: -0.0002

Data Index: 376090 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0268. Min Act: -0.0002

Data Index: 413230 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0321. Min Act: -0.0002

Data Index: 312828 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1179485 (C4 (Web Text))

Max Activating Token Index: 74