Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1839 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0003

Data Index: 80900 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0383. Min Act: -0.0002

Data Index: 601053 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1038754 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0310. Min Act: -0.0004

Data Index: 1116818 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1228679 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1018660 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0266. Min Act: -0.0003

Data Index: 570765 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0252. Min Act: -0.0002

Data Index: 628936 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0264. Min Act: -0.0002

Data Index: 635785 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1175415 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1378118 (Python Code)

Max Activating Token Index: 375

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0251. Min Act: -0.0003

Data Index: 589258 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0251. Min Act: -0.0002

Data Index: 281252 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1517769 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0235. Min Act: -0.0002

Data Index: 624274 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0230. Min Act: -0.0002

Data Index: 190473 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0241. Min Act: -0.0000

Data Index: 814310 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0215. Min Act: -0.0003

Data Index: 737444 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0232. Min Act: -0.0002

Data Index: 149056 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1395687 (Python Code)

Max Activating Token Index: 245