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

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

Neuron 4978 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1594371 (Python Code)

Max Activating Token Index: 685

Text #1

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1500. Min Act: -0.0001

Data Index: 1457247 (Python Code)

Max Activating Token Index: 629

Text #2

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1446854 (Python Code)

Max Activating Token Index: 824

Text #3

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1372980 (Python Code)

Max Activating Token Index: 734

Text #4

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1620091 (Python Code)

Max Activating Token Index: 262

Text #5

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1586687 (Python Code)

Max Activating Token Index: 841

Text #6

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1522199 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1601197 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1651635 (Python Code)

Max Activating Token Index: 590

Text #9

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1409092 (Python Code)

Max Activating Token Index: 727

Text #10

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1386957 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1269. Min Act: -0.0000

Data Index: 1535510 (Python Code)

Max Activating Token Index: 162

Text #12

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1535259 (Python Code)

Max Activating Token Index: 788

Text #13

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1584139 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1514131 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1650540 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1377224 (Python Code)

Max Activating Token Index: 668

Text #17

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1547337 (Python Code)

Max Activating Token Index: 680

Text #18

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1434521 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1380126 (Python Code)

Max Activating Token Index: 699