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

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

Neuron 1906 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0285. Min Act: -0.0005

Data Index: 644659 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0273. Min Act: -0.0006

Data Index: 677658 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0263. Min Act: -0.0005

Data Index: 550144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0259. Min Act: -0.0005

Data Index: 1531712 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0251. Min Act: -0.0005

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1647722 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0252. Min Act: -0.0005

Data Index: 844187 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0246. Min Act: -0.0006

Data Index: 82366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0232. Min Act: -0.0005

Data Index: 1567872 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0231. Min Act: -0.0006

Data Index: 245530 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0229. Min Act: -0.0005

Data Index: 1628446 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0226. Min Act: -0.0006

Data Index: 580283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0225. Min Act: -0.0006

Data Index: 553120 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0226. Min Act: -0.0004

Data Index: 1546129 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0222. Min Act: -0.0005

Data Index: 1404121 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1123172 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0219. Min Act: -0.0005

Data Index: 1653666 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0225. Min Act: -0.0006

Data Index: 958504 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1643146 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1521031 (Python Code)

Max Activating Token Index: 1023