Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3158 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1658. Min Act: -0.0001

Data Index: 433206 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1032853 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1567. Min Act: -0.0001

Data Index: 235199 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1446. Min Act: -0.0002

Data Index: 164517 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1516. Min Act: -0.0002

Data Index: 227287 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1156304 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1322498 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1321. Min Act: -0.0002

Data Index: 962245 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1322. Min Act: -0.0002

Data Index: 871947 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1350. Min Act: -0.0001

Data Index: 184860 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1354047 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1270. Min Act: -0.0001

Data Index: 838725 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1265. Min Act: -0.0001

Data Index: 669878 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1016407 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1249. Min Act: -0.0001

Data Index: 128445 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1301. Min Act: -0.0001

Data Index: 221133 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1243. Min Act: -0.0001

Data Index: 298381 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1187. Min Act: -0.0001

Data Index: 931698 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1224. Min Act: -0.0002

Data Index: 749447 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1228. Min Act: -0.0002

Data Index: 804316 (C4 (Web Text))

Max Activating Token Index: 727