Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 960 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0006

Data Index: 560841 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0217. Min Act: -0.0006

Data Index: 425093 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0216. Min Act: -0.0006

Data Index: 482028 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0210. Min Act: -0.0006

Data Index: 547680 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1256708 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0208. Min Act: -0.0006

Data Index: 740228 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1103003 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0210. Min Act: -0.0005

Data Index: 176864 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0209. Min Act: -0.0006

Data Index: 986742 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0214. Min Act: -0.0005

Data Index: 657541 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1064871 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0205. Min Act: -0.0006

Data Index: 539110 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0205. Min Act: -0.0006

Data Index: 531634 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0203. Min Act: -0.0006

Data Index: 623251 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0202. Min Act: -0.0006

Data Index: 714671 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0197. Min Act: -0.0006

Data Index: 288114 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1068374 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0201. Min Act: -0.0006

Data Index: 276586 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1335878 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0201. Min Act: -0.0006

Data Index: 743328 (C4 (Web Text))

Max Activating Token Index: 628