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

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

Neuron 1562 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2268. Min Act: -0.0000

Data Index: 446584 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2152. Min Act: -0.0000

Data Index: 542553 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1058050 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1004993 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1634. Min Act: -0.0000

Data Index: 979922 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1329. Min Act: -0.0000

Data Index: 932830 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1421750 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1585834 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1295. Min Act: -0.0000

Data Index: 1594489 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1210. Min Act: -0.0000

Data Index: 639372 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1222. Min Act: -0.0000

Data Index: 350324 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1266. Min Act: -0.0000

Data Index: 472707 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1301552 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1563306 (Python Code)

Max Activating Token Index: 367

Text #14

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1237. Min Act: -0.0000

Data Index: 12742 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1505016 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1623972 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1490783 (Python Code)

Max Activating Token Index: 139

Text #18

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1407870 (Python Code)

Max Activating Token Index: 243

Text #19

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1150. Min Act: -0.0000

Data Index: 217349 (C4 (Web Text))

Max Activating Token Index: 96