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

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

Neuron 632 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1886. Min Range: -1.1886

Max Act: 1.1886. Min Act: -0.0002

Data Index: 1652746 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 1.1886. Min Range: -1.1886

Max Act: 1.1593. Min Act: -0.0002

Data Index: 1506743 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 1.1886. Min Range: -1.1886

Max Act: 1.0511. Min Act: -0.0002

Data Index: 1510659 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 1.1886. Min Range: -1.1886

Max Act: 1.0238. Min Act: -0.0002

Data Index: 1474335 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8713. Min Act: -0.0002

Data Index: 1429501 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9037. Min Act: -0.0002

Data Index: 1590808 (Python Code)

Max Activating Token Index: 477

Text #6

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8252. Min Act: -0.0002

Data Index: 1605224 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8378. Min Act: -0.0002

Data Index: 1430381 (Python Code)

Max Activating Token Index: 130

Text #8

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8286. Min Act: -0.0002

Data Index: 1610820 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9109. Min Act: -0.0002

Data Index: 1404011 (Python Code)

Max Activating Token Index: 33

Text #10

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8765. Min Act: -0.0002

Data Index: 1429107 (Python Code)

Max Activating Token Index: 305

Text #11

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.7995. Min Act: -0.0002

Data Index: 1412618 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8783. Min Act: -0.0002

Data Index: 1438124 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8505. Min Act: -0.0002

Data Index: 1437592 (Python Code)

Max Activating Token Index: 25

Text #14

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8370. Min Act: -0.0002

Data Index: 1362817 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.7428. Min Act: -0.0002

Data Index: 1530728 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.7885. Min Act: -0.0002

Data Index: 1462741 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8128. Min Act: -0.0002

Data Index: 1385650 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.7684. Min Act: -0.0002

Data Index: 1531851 (Python Code)

Max Activating Token Index: 493

Text #19

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8656. Min Act: -0.0002

Data Index: 1578480 (Python Code)

Max Activating Token Index: 10