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

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

Neuron 1504 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0246. Min Act: -0.0006

Data Index: 91916 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1162798 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0235. Min Act: -0.0005

Data Index: 834740 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0240. Min Act: -0.0005

Data Index: 961964 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0238. Min Act: -0.0005

Data Index: 780839 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0237. Min Act: -0.0005

Data Index: 469015 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0237. Min Act: -0.0005

Data Index: 749694 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0242. Min Act: -0.0005

Data Index: 1205652 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0231. Min Act: -0.0005

Data Index: 463500 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0231. Min Act: -0.0006

Data Index: 439567 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0229. Min Act: -0.0005

Data Index: 237548 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0238. Min Act: -0.0005

Data Index: 741681 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0227. Min Act: -0.0005

Data Index: 1320536 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1353422 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0225. Min Act: -0.0005

Data Index: 1067938 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0224. Min Act: -0.0005

Data Index: 726986 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0217. Min Act: -0.0005

Data Index: 1115930 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0222. Min Act: -0.0005

Data Index: 718259 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0222. Min Act: -0.0005

Data Index: 593032 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0227. Min Act: -0.0005

Data Index: 1316820 (C4 (Web Text))

Max Activating Token Index: 1011