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

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

Neuron 4705 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: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1358240 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0357. Min Act: -0.0002

Data Index: 542693 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0300. Min Act: -0.0002

Data Index: 338575 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0258. Min Act: -0.0002

Data Index: 960985 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1475071 (Python Code)

Max Activating Token Index: 946

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1403475 (Python Code)

Max Activating Token Index: 978

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0255. Min Act: -0.0002

Data Index: 855357 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0259. Min Act: -0.0002

Data Index: 812422 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0239. Min Act: -0.0002

Data Index: 309746 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1560288 (Python Code)

Max Activating Token Index: 621

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0246. Min Act: -0.0002

Data Index: 477037 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0227. Min Act: -0.0002

Data Index: 882877 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1632130 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0221. Min Act: -0.0002

Data Index: 778350 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0217. Min Act: -0.0002

Data Index: 215200 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0198. Min Act: -0.0002

Data Index: 398826 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0204. Min Act: -0.0002

Data Index: 856091 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1449775 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0205. Min Act: -0.0002

Data Index: 694245 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1428691 (Python Code)

Max Activating Token Index: 634