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

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

Neuron 1444 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1554514 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9813. Min Act: -0.0001

Data Index: 673707 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9611. Min Act: -0.0001

Data Index: 1487605 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9552. Min Act: -0.0001

Data Index: 323472 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1457468 (Python Code)

Max Activating Token Index: 596

Text #5

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9001. Min Act: -0.0001

Data Index: 833935 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8116. Min Act: -0.0001

Data Index: 1131507 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7640. Min Act: -0.0001

Data Index: 263645 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8652. Min Act: -0.0001

Data Index: 1407663 (Python Code)

Max Activating Token Index: 665

Text #9

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8377. Min Act: -0.0001

Data Index: 937090 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8333. Min Act: -0.0001

Data Index: 945822 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8472. Min Act: -0.0001

Data Index: 1057996 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8384. Min Act: -0.0001

Data Index: 1162668 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7298. Min Act: -0.0001

Data Index: 169641 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8229. Min Act: -0.0000

Data Index: 604967 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7643. Min Act: -0.0001

Data Index: 410206 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7882. Min Act: -0.0001

Data Index: 1552593 (Python Code)

Max Activating Token Index: 956

Text #17

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1471837 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7666. Min Act: -0.0001

Data Index: 650036 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7849. Min Act: -0.0001

Data Index: 484912 (C4 (Web Text))

Max Activating Token Index: 829