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

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

Neuron 3595 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: 0.0454. Min Range: -0.0454

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1221733 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0300. Min Act: -0.0002

Data Index: 255538 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1584012 (Python Code)

Max Activating Token Index: 438

Text #3

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1008281 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0212. Min Act: -0.0002

Data Index: 264449 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1568079 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0300. Min Act: -0.0002

Data Index: 383786 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0249. Min Act: -0.0002

Data Index: 731288 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1490201 (Python Code)

Max Activating Token Index: 227

Text #9

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1555930 (Python Code)

Max Activating Token Index: 604

Text #10

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0229. Min Act: -0.0002

Data Index: 681204 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0229. Min Act: -0.0002

Data Index: 604838 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1425558 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1065224 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1458361 (Python Code)

Max Activating Token Index: 802

Text #15

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1651322 (Python Code)

Max Activating Token Index: 371

Text #16

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1342373 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0234. Min Act: -0.0002

Data Index: 461689 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1283954 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0210. Min Act: -0.0002

Data Index: 397424 (C4 (Web Text))

Max Activating Token Index: 1011