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

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

Neuron 3348 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: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0003

Data Index: 33231 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0301. Min Act: -0.0003

Data Index: 957222 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1355513 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0225. Min Act: -0.0003

Data Index: 571247 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0184. Min Act: -0.0003

Data Index: 34007 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0219. Min Act: -0.0003

Data Index: 217680 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0207. Min Act: -0.0003

Data Index: 997706 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0189. Min Act: -0.0003

Data Index: 538371 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0199. Min Act: -0.0003

Data Index: 12439 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0194. Min Act: -0.0003

Data Index: 491518 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0192. Min Act: -0.0003

Data Index: 345138 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1230017 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0192. Min Act: -0.0003

Data Index: 287556 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0159. Min Act: -0.0002

Data Index: 759845 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0188. Min Act: -0.0003

Data Index: 25286 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0184. Min Act: -0.0003

Data Index: 689900 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1186623 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0184. Min Act: -0.0003

Data Index: 130249 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1303375 (C4 (Web Text))

Max Activating Token Index: 68