Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2571 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.8724. Min Act: -0.0000

Data Index: 1366075 (Python Code)

Max Activating Token Index: 314

Text #1

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.4087. Min Act: -0.0000

Data Index: 1511007 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1632693 (Python Code)

Max Activating Token Index: 604

Text #3

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1620. Min Act: -0.0000

Data Index: 1532191 (Python Code)

Max Activating Token Index: 671

Text #4

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1512726 (Python Code)

Max Activating Token Index: 444

Text #5

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1472940 (Python Code)

Max Activating Token Index: 704

Text #6

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1436682 (Python Code)

Max Activating Token Index: 704

Text #7

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1479198 (Python Code)

Max Activating Token Index: 356

Text #8

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1651363 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1527230 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1540479 (Python Code)

Max Activating Token Index: 211

Text #11

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1454528 (Python Code)

Max Activating Token Index: 373

Text #12

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1635679 (Python Code)

Max Activating Token Index: 345

Text #13

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1380607 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1513658 (Python Code)

Max Activating Token Index: 475

Text #15

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1397635 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1450389 (Python Code)

Max Activating Token Index: 553

Text #17

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1444129 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1459324 (Python Code)

Max Activating Token Index: 516

Text #19

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1405040 (Python Code)

Max Activating Token Index: 54