Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 784 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0322. Min Act: -0.0002

Data Index: 78177 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1425197 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0239. Min Act: -0.0002

Data Index: 472900 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0223. Min Act: -0.0002

Data Index: 882887 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1238676 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0222. Min Act: -0.0002

Data Index: 942633 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1159974 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1059444 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0202. Min Act: -0.0002

Data Index: 730290 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0195. Min Act: -0.0002

Data Index: 81832 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0191. Min Act: -0.0002

Data Index: 598434 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0187. Min Act: -0.0002

Data Index: 365312 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1476580 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0191. Min Act: -0.0002

Data Index: 129644 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1102812 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0180. Min Act: -0.0002

Data Index: 111871 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0185. Min Act: -0.0002

Data Index: 797402 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0181. Min Act: -0.0002

Data Index: 742230 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0180. Min Act: -0.0002

Data Index: 458664 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0176. Min Act: -0.0002

Data Index: 168556 (C4 (Web Text))

Max Activating Token Index: 984