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

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

Neuron 5062 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0270. Min Act: -0.0000

Data Index: 789408 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0262. Min Act: -0.0000

Data Index: 790790 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0256. Min Act: -0.0000

Data Index: 697488 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0217. Min Act: -0.0000

Data Index: 118914 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0217. Min Act: -0.0000

Data Index: 366277 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0208. Min Act: -0.0000

Data Index: 1394053 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0205. Min Act: -0.0000

Data Index: 1515981 (Python Code)

Max Activating Token Index: 737

Text #7

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0188. Min Act: -0.0000

Data Index: 1271063 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0176. Min Act: -0.0000

Data Index: 362472 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0196. Min Act: -0.0000

Data Index: 1606835 (Python Code)

Max Activating Token Index: 771

Text #10

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0197. Min Act: -0.0000

Data Index: 754748 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0186. Min Act: -0.0000

Data Index: 1102210 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0179. Min Act: -0.0000

Data Index: 1551671 (Python Code)

Max Activating Token Index: 266

Text #13

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0189. Min Act: -0.0000

Data Index: 1142122 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0187. Min Act: -0.0000

Data Index: 1382555 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0177. Min Act: -0.0000

Data Index: 538474 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0179. Min Act: -0.0000

Data Index: 1147602 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0184. Min Act: -0.0000

Data Index: 230421 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1242194 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0177. Min Act: -0.0000

Data Index: 1280718 (C4 (Web Text))

Max Activating Token Index: 627