Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1182 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0003

Data Index: 1460330 (Python Code)

Max Activating Token Index: 427

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1453. Min Act: -0.0003

Data Index: 1409610 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1391. Min Act: -0.0003

Data Index: 1641069 (Python Code)

Max Activating Token Index: 563

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1416. Min Act: -0.0003

Data Index: 1648291 (Python Code)

Max Activating Token Index: 733

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1256. Min Act: -0.0003

Data Index: 1507709 (Python Code)

Max Activating Token Index: 382

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1204. Min Act: -0.0003

Data Index: 1636714 (Python Code)

Max Activating Token Index: 135

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1234. Min Act: -0.0003

Data Index: 1494344 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1195. Min Act: -0.0003

Data Index: 1456943 (Python Code)

Max Activating Token Index: 58

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1195. Min Act: -0.0003

Data Index: 1417270 (Python Code)

Max Activating Token Index: 560

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1155. Min Act: -0.0003

Data Index: 1548586 (Python Code)

Max Activating Token Index: 174

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1202. Min Act: -0.0003

Data Index: 1548289 (Python Code)

Max Activating Token Index: 925

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1122. Min Act: -0.0003

Data Index: 1495395 (Python Code)

Max Activating Token Index: 527

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1155. Min Act: -0.0003

Data Index: 1492305 (Python Code)

Max Activating Token Index: 696

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1155. Min Act: -0.0003

Data Index: 1455027 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1104. Min Act: -0.0004

Data Index: 1464444 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1375656 (Python Code)

Max Activating Token Index: 283

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1459568 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1042. Min Act: -0.0003

Data Index: 1479166 (Python Code)

Max Activating Token Index: 769

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1057. Min Act: -0.0003

Data Index: 1457215 (Python Code)

Max Activating Token Index: 664

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1059. Min Act: -0.0003

Data Index: 1377756 (Python Code)

Max Activating Token Index: 979