Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1555790 (Python Code)

Max Activating Token Index: 1006

Text #1

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1409773 (Python Code)

Max Activating Token Index: 940

Text #2

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1627173 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1552573 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1644575 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1572437 (Python Code)

Max Activating Token Index: 146

Text #6

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0217. Min Act: -0.0004

Data Index: 20772 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1594831 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1403893 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1506883 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1604612 (Python Code)

Max Activating Token Index: 131

Text #11

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1558194 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1375594 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1617365 (Python Code)

Max Activating Token Index: 55

Text #14

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1610257 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1533675 (Python Code)

Max Activating Token Index: 352

Text #16

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1370060 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1650233 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1391189 (Python Code)

Max Activating Token Index: 621

Text #19

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1603459 (Python Code)

Max Activating Token Index: 534