Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1784 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1117455 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0241. Min Act: -0.0006

Data Index: 574010 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0255. Min Act: -0.0006

Data Index: 608093 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0236. Min Act: -0.0006

Data Index: 630182 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1096807 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0221. Min Act: -0.0006

Data Index: 322565 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1051257 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0223. Min Act: -0.0006

Data Index: 505762 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1093346 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0220. Min Act: -0.0006

Data Index: 629955 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0218. Min Act: -0.0006

Data Index: 248337 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1231313 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0211. Min Act: -0.0006

Data Index: 665032 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0219. Min Act: -0.0006

Data Index: 746074 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0209. Min Act: -0.0006

Data Index: 67214 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1601155 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0212. Min Act: -0.0006

Data Index: 245925 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0006

Data Index: 967008 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1353901 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0205. Min Act: -0.0006

Data Index: 299326 (C4 (Web Text))

Max Activating Token Index: 498