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

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

Neuron 289 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1533226 (Python Code)

Max Activating Token Index: 277

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1588874 (Python Code)

Max Activating Token Index: 747

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1655602 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1402891 (Python Code)

Max Activating Token Index: 83

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1646536 (Python Code)

Max Activating Token Index: 94

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1399356 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0224. Min Act: -0.0005

Data Index: 645631 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1569749 (Python Code)

Max Activating Token Index: 321

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1476210 (Python Code)

Max Activating Token Index: 817

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1379326 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1612622 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1634865 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1486450 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1623183 (Python Code)

Max Activating Token Index: 503

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1471345 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1529072 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0210. Min Act: -0.0006

Data Index: 778332 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0210. Min Act: -0.0006

Data Index: 426525 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1463297 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1422129 (Python Code)

Max Activating Token Index: 268