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

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

Neuron 2416 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2779. Min Act: -0.0000

Data Index: 315869 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2626. Min Act: -0.0000

Data Index: 723787 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2611. Min Act: -0.0000

Data Index: 912563 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1395028 (Python Code)

Max Activating Token Index: 847

Text #4

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2477. Min Act: -0.0000

Data Index: 748899 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1242185 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2445. Min Act: -0.0000

Data Index: 881389 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2269. Min Act: -0.0000

Data Index: 844854 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2311. Min Act: -0.0000

Data Index: 493505 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2308. Min Act: -0.0000

Data Index: 46108 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1090546 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1308997 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1234522 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1112464 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2090. Min Act: -0.0000

Data Index: 355618 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1884. Min Act: -0.0000

Data Index: 211130 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1443838 (Python Code)

Max Activating Token Index: 605

Text #17

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1910. Min Act: -0.0000

Data Index: 879133 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1948. Min Act: -0.0000

Data Index: 372804 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1862. Min Act: -0.0000

Data Index: 456473 (C4 (Web Text))

Max Activating Token Index: 565