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

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

Neuron 4280 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0025. Min Act: -0.0002

Data Index: 778816 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 170333 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 213426 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 410440 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 624160 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 629318 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 826600 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 584759 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 951701 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 92912 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1013107 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1288310 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 11614 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1304684 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1278161 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1222134 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1327376 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0021. Min Act: -0.0002

Data Index: 915265 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 430833 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1038389 (C4 (Web Text))

Max Activating Token Index: 659