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

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

Neuron 576 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: 0.0265. Min Range: -0.0265

Max Act: 0.0265. Min Act: -0.0006

Data Index: 340336 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0256. Min Act: -0.0006

Data Index: 195673 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0250. Min Act: -0.0006

Data Index: 592127 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0235. Min Act: -0.0006

Data Index: 655483 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0222. Min Act: -0.0006

Data Index: 933806 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0211. Min Act: -0.0006

Data Index: 279361 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1301970 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0218. Min Act: -0.0006

Data Index: 431778 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0221. Min Act: -0.0006

Data Index: 40721 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0216. Min Act: -0.0006

Data Index: 65421 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1025240 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0213. Min Act: -0.0006

Data Index: 252713 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0208. Min Act: -0.0007

Data Index: 481212 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0210. Min Act: -0.0006

Data Index: 430001 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1059175 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0209. Min Act: -0.0006

Data Index: 980764 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0209. Min Act: -0.0006

Data Index: 341550 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0213. Min Act: -0.0006

Data Index: 942988 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0203. Min Act: -0.0006

Data Index: 291662 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0202. Min Act: -0.0006

Data Index: 11710 (C4 (Web Text))

Max Activating Token Index: 163