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

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

Neuron 3903 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1376690 (Python Code)

Max Activating Token Index: 258

Text #1

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1711. Min Act: -0.0001

Data Index: 1491132 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1457478 (Python Code)

Max Activating Token Index: 749

Text #3

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1390863 (Python Code)

Max Activating Token Index: 837

Text #4

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1527979 (Python Code)

Max Activating Token Index: 383

Text #5

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1636916 (Python Code)

Max Activating Token Index: 483

Text #6

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1434. Min Act: -0.0001

Data Index: 1511812 (Python Code)

Max Activating Token Index: 493

Text #7

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1391201 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1401766 (Python Code)

Max Activating Token Index: 237

Text #9

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1398916 (Python Code)

Max Activating Token Index: 1018

Text #10

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1516563 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1637469 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1401361 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1520585 (Python Code)

Max Activating Token Index: 545

Text #14

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1562170 (Python Code)

Max Activating Token Index: 998

Text #15

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1506491 (Python Code)

Max Activating Token Index: 544

Text #16

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1494640 (Python Code)

Max Activating Token Index: 443

Text #17

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1499714 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1537519 (Python Code)

Max Activating Token Index: 176

Text #19

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1587081 (Python Code)

Max Activating Token Index: 292