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

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

Neuron 1489 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1496392 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1448273 (Python Code)

Max Activating Token Index: 544

Text #2

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1475747 (Python Code)

Max Activating Token Index: 941

Text #3

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1645862 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1494193 (Python Code)

Max Activating Token Index: 924

Text #5

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1443190 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1375786 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1640387 (Python Code)

Max Activating Token Index: 406

Text #8

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1489837 (Python Code)

Max Activating Token Index: 757

Text #9

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1578084 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1598412 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1598091 (Python Code)

Max Activating Token Index: 261

Text #12

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1493867 (Python Code)

Max Activating Token Index: 841

Text #13

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1500506 (Python Code)

Max Activating Token Index: 282

Text #14

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1473108 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1457536 (Python Code)

Max Activating Token Index: 130

Text #16

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1606516 (Python Code)

Max Activating Token Index: 885

Text #17

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1496806 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1447458 (Python Code)

Max Activating Token Index: 688

Text #19

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1196271 (C4 (Web Text))

Max Activating Token Index: 114