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

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

Neuron 853 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1519. Min Range: -2.1519

Max Act: 2.1519. Min Act: -0.0000

Data Index: 1553244 (Python Code)

Max Activating Token Index: 168

Text #1

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.6667. Min Act: -0.0000

Data Index: 1490044 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.4333. Min Act: 0.0000

Data Index: 1541020 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.2806. Min Act: 0.0000

Data Index: 1511781 (Python Code)

Max Activating Token Index: 154

Text #4

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1384737 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.2842. Min Act: -0.0000

Data Index: 1418919 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.1740. Min Act: 0.0000

Data Index: 1445788 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1545548 (Python Code)

Max Activating Token Index: 332

Text #8

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1459288 (Python Code)

Max Activating Token Index: 388

Text #9

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.2035. Min Act: 0.0000

Data Index: 1399587 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1560595 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.1761. Min Act: -0.0000

Data Index: 1486806 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.1436. Min Act: 0.0000

Data Index: 1460792 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1370798 (Python Code)

Max Activating Token Index: 484

Text #14

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.0430. Min Act: 0.0000

Data Index: 1655476 (Python Code)

Max Activating Token Index: 205

Text #15

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.0570. Min Act: 0.0000

Data Index: 1515491 (Python Code)

Max Activating Token Index: 535

Text #16

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.1707. Min Act: 0.0000

Data Index: 1416493 (Python Code)

Max Activating Token Index: 450

Text #17

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1525984 (Python Code)

Max Activating Token Index: 608

Text #18

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1559018 (Python Code)

Max Activating Token Index: 951

Text #19

Max Range: 2.1519. Min Range: -2.1519

Max Act: 1.0769. Min Act: 0.0000

Data Index: 1503394 (Python Code)

Max Activating Token Index: 297