Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 25 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2720. Min Act: -0.0001

Data Index: 1140808 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2679. Min Act: -0.0001

Data Index: 1314451 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2024. Min Act: -0.0000

Data Index: 492113 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1838. Min Act: -0.0001

Data Index: 65230 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1823. Min Act: -0.0001

Data Index: 783735 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1760. Min Act: -0.0001

Data Index: 154448 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1739. Min Act: -0.0001

Data Index: 900449 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1742. Min Act: -0.0000

Data Index: 362871 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1718. Min Act: -0.0000

Data Index: 116858 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1720. Min Act: -0.0001

Data Index: 18531 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1765. Min Act: -0.0000

Data Index: 419596 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1696. Min Act: -0.0001

Data Index: 250282 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1696. Min Act: -0.0001

Data Index: 15240 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1745. Min Act: -0.0000

Data Index: 18535 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1675. Min Act: -0.0000

Data Index: 403535 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1239193 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1669. Min Act: -0.0001

Data Index: 979089 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1294932 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1193101 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1629. Min Act: -0.0000

Data Index: 394901 (C4 (Web Text))

Max Activating Token Index: 659