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

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

Neuron 1225 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1380647 (Python Code)

Max Activating Token Index: 991

Text #1

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1348. Min Act: 0.0000

Data Index: 1386689 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1349. Min Act: 0.0001

Data Index: 1612416 (Python Code)

Max Activating Token Index: 488

Text #3

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1472212 (Python Code)

Max Activating Token Index: 227

Text #4

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1498661 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1263. Min Act: 0.0001

Data Index: 1539632 (Python Code)

Max Activating Token Index: 610

Text #6

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1580706 (Python Code)

Max Activating Token Index: 534

Text #7

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1216. Min Act: 0.0000

Data Index: 1402776 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1446102 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1222. Min Act: 0.0000

Data Index: 1444293 (Python Code)

Max Activating Token Index: 625

Text #10

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1471825 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1173. Min Act: 0.0000

Data Index: 1381566 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1275. Min Act: 0.0000

Data Index: 1634915 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1589678 (Python Code)

Max Activating Token Index: 912

Text #14

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1621092 (Python Code)

Max Activating Token Index: 368

Text #15

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1385711 (Python Code)

Max Activating Token Index: 165

Text #16

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1162. Min Act: 0.0001

Data Index: 1515231 (Python Code)

Max Activating Token Index: 258

Text #17

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1271. Min Act: 0.0000

Data Index: 1574438 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1365820 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1539940 (Python Code)

Max Activating Token Index: 275