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

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

Neuron 4949 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: 0.9436. Min Range: -0.9436

Max Act: 0.9405. Min Act: -0.0002

Data Index: 332305 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.9436. Min Act: -0.0002

Data Index: 742065 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8837. Min Act: -0.0002

Data Index: 531577 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8329. Min Act: -0.0002

Data Index: 348597 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.9061. Min Act: -0.0002

Data Index: 761741 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8244. Min Act: -0.0002

Data Index: 400319 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7864. Min Act: -0.0002

Data Index: 1277728 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8464. Min Act: -0.0002

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8481. Min Act: -0.0002

Data Index: 984905 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8421. Min Act: -0.0002

Data Index: 217546 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8248. Min Act: -0.0002

Data Index: 384699 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8400. Min Act: -0.0002

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8102. Min Act: -0.0002

Data Index: 1017184 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7997. Min Act: -0.0002

Data Index: 1177874 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8511. Min Act: -0.0002

Data Index: 250528 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7716. Min Act: -0.0002

Data Index: 368701 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8509. Min Act: -0.0002

Data Index: 661064 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7736. Min Act: -0.0002

Data Index: 208927 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7899. Min Act: -0.0002

Data Index: 939645 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8084. Min Act: -0.0002

Data Index: 1292966 (C4 (Web Text))

Max Activating Token Index: 424