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

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

Neuron 2326 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1459061 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1396833 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1450723 (Python Code)

Max Activating Token Index: 165

Text #3

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1618940 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1570377 (Python Code)

Max Activating Token Index: 145

Text #5

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1421489 (Python Code)

Max Activating Token Index: 402

Text #6

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1586778 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1297. Min Act: -0.0001

Data Index: 1495141 (Python Code)

Max Activating Token Index: 873

Text #8

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1606377 (Python Code)

Max Activating Token Index: 800

Text #9

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1644387 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1464587 (Python Code)

Max Activating Token Index: 306

Text #11

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1618105 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1602368 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1550232 (Python Code)

Max Activating Token Index: 172

Text #14

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1412302 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1423412 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1399952 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1449506 (Python Code)

Max Activating Token Index: 931

Text #18

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1457265 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1408392 (Python Code)

Max Activating Token Index: 684