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

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

Neuron 3594 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: 1.0511. Min Range: -1.0511

Max Act: 1.0511. Min Act: -0.0000

Data Index: 743776 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.8228. Min Act: -0.0000

Data Index: 526883 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1086380 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6759. Min Act: -0.0000

Data Index: 151275 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.7301. Min Act: 0.0002

Data Index: 230448 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6519. Min Act: -0.0000

Data Index: 469462 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6964. Min Act: 0.0000

Data Index: 154392 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6908. Min Act: -0.0000

Data Index: 195279 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6508. Min Act: -0.0000

Data Index: 436319 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1089798 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6100. Min Act: -0.0000

Data Index: 907947 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5782. Min Act: -0.0000

Data Index: 308716 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5919. Min Act: 0.0000

Data Index: 227421 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1229276 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5940. Min Act: -0.0000

Data Index: 247864 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5733. Min Act: -0.0000

Data Index: 386688 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5538. Min Act: -0.0000

Data Index: 952283 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5499. Min Act: -0.0000

Data Index: 594516 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5358. Min Act: -0.0000

Data Index: 212156 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5843. Min Act: -0.0000

Data Index: 411011 (C4 (Web Text))

Max Activating Token Index: 315