Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 390 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1632. Min Act: -0.0002

Data Index: 1146711 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1438. Min Act: -0.0002

Data Index: 590278 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1448. Min Act: -0.0002

Data Index: 667838 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1342. Min Act: -0.0002

Data Index: 911013 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1281. Min Act: -0.0002

Data Index: 888704 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1286. Min Act: -0.0001

Data Index: 426115 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1282. Min Act: -0.0002

Data Index: 410116 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1306. Min Act: -0.0002

Data Index: 1168693 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1261. Min Act: -0.0002

Data Index: 1074643 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1235. Min Act: -0.0002

Data Index: 169463 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1225. Min Act: -0.0002

Data Index: 626411 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1211. Min Act: -0.0002

Data Index: 928505 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1195. Min Act: -0.0002

Data Index: 313827 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1205. Min Act: -0.0002

Data Index: 152544 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1225. Min Act: -0.0002

Data Index: 306125 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1189. Min Act: -0.0002

Data Index: 1326110 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1150. Min Act: -0.0002

Data Index: 272948 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1346382 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1218385 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1185. Min Act: -0.0002

Data Index: 78746 (C4 (Web Text))

Max Activating Token Index: 438