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

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

Neuron 1913 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: 0.0313. Min Range: -0.0313

Max Act: 0.0304. Min Act: -0.0002

Data Index: 576674 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1618435 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0289. Min Act: -0.0002

Data Index: 450822 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1397654 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1210823 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0293. Min Act: -0.0002

Data Index: 883702 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0284. Min Act: -0.0002

Data Index: 286602 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1464287 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0237. Min Act: -0.0002

Data Index: 290220 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0266. Min Act: -0.0002

Data Index: 851466 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0266. Min Act: -0.0002

Data Index: 663728 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1315914 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1338844 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0243. Min Act: -0.0002

Data Index: 753906 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0255. Min Act: -0.0002

Data Index: 27204 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1367179 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0253. Min Act: -0.0002

Data Index: 287019 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0245. Min Act: -0.0002

Data Index: 143619 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0261. Min Act: -0.0002

Data Index: 357735 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0224. Min Act: -0.0002

Data Index: 529586 (C4 (Web Text))

Max Activating Token Index: 277