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

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

Neuron 3426 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.7121. Min Act: -0.0000

Data Index: 1430663 (Python Code)

Max Activating Token Index: 952

Text #1

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.8358. Min Act: -0.0000

Data Index: 1641638 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.9335. Min Act: -0.0000

Data Index: 1456418 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.7733. Min Act: -0.0000

Data Index: 1415720 (Python Code)

Max Activating Token Index: 680

Text #4

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.5987. Min Act: -0.0000

Data Index: 1446805 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.6542. Min Act: -0.0000

Data Index: 1457694 (Python Code)

Max Activating Token Index: 72

Text #6

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.5804. Min Act: -0.0000

Data Index: 1514797 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.4744. Min Act: -0.0000

Data Index: 1513188 (Python Code)

Max Activating Token Index: 252

Text #8

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.4688. Min Act: -0.0000

Data Index: 1566529 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.3282. Min Act: -0.0000

Data Index: 1592816 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.3255. Min Act: -0.0000

Data Index: 1528157 (Python Code)

Max Activating Token Index: 357

Text #11

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.3895. Min Act: -0.0000

Data Index: 1627412 (Python Code)

Max Activating Token Index: 304

Text #12

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.1751. Min Act: -0.0000

Data Index: 1452573 (Python Code)

Max Activating Token Index: 359

Text #13

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.3895. Min Act: -0.0000

Data Index: 1506037 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.2209. Min Act: -0.0000

Data Index: 1406405 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.0750. Min Act: -0.0000

Data Index: 1568882 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.4176. Min Act: -0.0000

Data Index: 1406588 (Python Code)

Max Activating Token Index: 303

Text #17

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.1497. Min Act: -0.0000

Data Index: 1618178 (Python Code)

Max Activating Token Index: 571

Text #18

Max Range: 2.9335. Min Range: -2.9335

Max Act: 2.1611. Min Act: -0.0000

Data Index: 1596472 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 2.9335. Min Range: -2.9335

Max Act: 1.9910. Min Act: -0.0000

Data Index: 1444362 (Python Code)

Max Activating Token Index: 79