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

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

Neuron 2013 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0563. Min Act: -0.0002

Data Index: 85214 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0520. Min Act: -0.0002

Data Index: 383649 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0498. Min Act: -0.0002

Data Index: 621182 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0454. Min Act: -0.0002

Data Index: 811746 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0465. Min Act: -0.0002

Data Index: 27740 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1072860 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0413. Min Act: -0.0002

Data Index: 158203 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0390. Min Act: -0.0002

Data Index: 712335 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0378. Min Act: -0.0002

Data Index: 228114 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0377. Min Act: -0.0002

Data Index: 440057 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0377. Min Act: -0.0002

Data Index: 56756 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0379. Min Act: -0.0002

Data Index: 648281 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1050135 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0374. Min Act: -0.0002

Data Index: 476592 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0369. Min Act: -0.0002

Data Index: 760091 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0351. Min Act: -0.0002

Data Index: 204311 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1182514 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0359. Min Act: -0.0002

Data Index: 463616 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0363. Min Act: -0.0002

Data Index: 682131 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0381. Min Act: -0.0002

Data Index: 348237 (C4 (Web Text))

Max Activating Token Index: 151