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

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

Neuron 3871 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1515612 (Python Code)

Max Activating Token Index: 714

Text #1

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1440. Min Act: -0.0000

Data Index: 95774 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1345101 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1490. Min Act: -0.0000

Data Index: 138035 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1139099 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1520. Min Act: -0.0000

Data Index: 354167 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1040258 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1410. Min Act: -0.0000

Data Index: 520 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1228. Min Act: -0.0000

Data Index: 577917 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1366. Min Act: -0.0000

Data Index: 672416 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1400. Min Act: -0.0000

Data Index: 681653 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1259. Min Act: -0.0000

Data Index: 96975 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1290. Min Act: -0.0000

Data Index: 630341 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1248. Min Act: -0.0000

Data Index: 267721 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1205. Min Act: -0.0000

Data Index: 361989 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1310998 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1008674 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1317746 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1321792 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1235. Min Act: -0.0000

Data Index: 548241 (C4 (Web Text))

Max Activating Token Index: 120