Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 867 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0256. Min Act: -0.0000

Data Index: 987977 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0223. Min Act: -0.0000

Data Index: 255326 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0224. Min Act: -0.0000

Data Index: 1287371 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0218. Min Act: -0.0000

Data Index: 729215 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0238. Min Act: -0.0000

Data Index: 618545 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0210. Min Act: -0.0000

Data Index: 1496961 (Python Code)

Max Activating Token Index: 240

Text #6

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0232. Min Act: -0.0000

Data Index: 1064270 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0215. Min Act: -0.0000

Data Index: 837867 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0223. Min Act: -0.0000

Data Index: 1641566 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0209. Min Act: -0.0000

Data Index: 434392 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0209. Min Act: -0.0000

Data Index: 1233434 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0201. Min Act: -0.0000

Data Index: 648721 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0206. Min Act: -0.0000

Data Index: 939021 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0188. Min Act: -0.0000

Data Index: 495137 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0209. Min Act: -0.0000

Data Index: 1535159 (Python Code)

Max Activating Token Index: 639

Text #15

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0194. Min Act: -0.0000

Data Index: 799267 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0194. Min Act: -0.0000

Data Index: 389772 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0196. Min Act: -0.0000

Data Index: 269945 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0191. Min Act: -0.0000

Data Index: 1345753 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0189. Min Act: -0.0000

Data Index: 1216473 (C4 (Web Text))

Max Activating Token Index: 358