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

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

Neuron 1626 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: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0006

Data Index: 108082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1151730 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1271133 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0218. Min Act: -0.0006

Data Index: 144772 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0228. Min Act: -0.0006

Data Index: 613305 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0225. Min Act: -0.0006

Data Index: 618127 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0217. Min Act: -0.0006

Data Index: 614877 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1082832 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1263353 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0216. Min Act: -0.0006

Data Index: 1123038 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0208. Min Act: -0.0006

Data Index: 775926 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1317962 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1166699 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0216. Min Act: -0.0006

Data Index: 1303141 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0211. Min Act: -0.0006

Data Index: 361146 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1656755 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0006

Data Index: 350110 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0214. Min Act: -0.0006

Data Index: 871061 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0202. Min Act: -0.0006

Data Index: 585889 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0212. Min Act: -0.0006

Data Index: 264626 (C4 (Web Text))

Max Activating Token Index: 1023