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

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

Neuron 10 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1488101 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1000019 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1183593 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1571. Min Act: -0.0000

Data Index: 578571 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1434. Min Act: -0.0001

Data Index: 887341 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1360. Min Act: -0.0000

Data Index: 338613 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1411681 (Python Code)

Max Activating Token Index: 1007

Text #7

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1648240 (Python Code)

Max Activating Token Index: 895

Text #8

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1585287 (Python Code)

Max Activating Token Index: 245

Text #9

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1392871 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1072567 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1178973 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1341. Min Act: -0.0000

Data Index: 426992 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1592110 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1233. Min Act: -0.0000

Data Index: 248719 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1467312 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1573041 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1582428 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1610734 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1515942 (Python Code)

Max Activating Token Index: 45