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

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

Neuron 3860 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1241025 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0342. Min Act: -0.0001

Data Index: 47799 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0334. Min Act: -0.0001

Data Index: 369169 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1099028 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0217. Min Act: -0.0001

Data Index: 241373 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1425599 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0225. Min Act: -0.0001

Data Index: 277555 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0198. Min Act: -0.0001

Data Index: 497078 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0208. Min Act: -0.0001

Data Index: 557834 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1564570 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0181. Min Act: -0.0001

Data Index: 588856 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1249528 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0215. Min Act: -0.0001

Data Index: 588846 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1520393 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0207. Min Act: -0.0001

Data Index: 147390 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1572415 (Python Code)

Max Activating Token Index: 347

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0229. Min Act: -0.0001

Data Index: 919160 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0198. Min Act: -0.0001

Data Index: 111518 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1599624 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0201. Min Act: -0.0001

Data Index: 179428 (C4 (Web Text))

Max Activating Token Index: 631