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

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

Neuron 2840 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1814. Min Act: -0.0003

Data Index: 1113944 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1709. Min Act: -0.0003

Data Index: 1331837 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1393. Min Act: -0.0003

Data Index: 5454 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1388. Min Act: -0.0002

Data Index: 979484 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1483. Min Act: -0.0003

Data Index: 1237357 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1476. Min Act: -0.0002

Data Index: 398910 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1361. Min Act: -0.0003

Data Index: 768831 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1356. Min Act: -0.0003

Data Index: 13005 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1285. Min Act: -0.0003

Data Index: 563591 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1344. Min Act: -0.0003

Data Index: 15528 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1296. Min Act: -0.0003

Data Index: 33250 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1203. Min Act: -0.0002

Data Index: 1207517 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1185. Min Act: -0.0002

Data Index: 287661 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1209. Min Act: -0.0003

Data Index: 276232 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1245. Min Act: -0.0003

Data Index: 900273 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1195. Min Act: -0.0003

Data Index: 1168224 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1143. Min Act: -0.0003

Data Index: 1118533 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1145. Min Act: -0.0003

Data Index: 1319037 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1128. Min Act: -0.0003

Data Index: 1062579 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1028. Min Act: -0.0003

Data Index: 813609 (C4 (Web Text))

Max Activating Token Index: 967