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

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

Neuron 919 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2343. Min Act: -0.0001

Data Index: 438747 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2072. Min Act: -0.0001

Data Index: 172709 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2110. Min Act: -0.0001

Data Index: 981549 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2016. Min Act: -0.0001

Data Index: 616941 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1843. Min Act: -0.0001

Data Index: 1205590 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1853. Min Act: -0.0001

Data Index: 523039 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1862. Min Act: -0.0001

Data Index: 673705 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1160608 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1136732 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1647. Min Act: -0.0001

Data Index: 659296 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1535. Min Act: -0.0001

Data Index: 601839 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1756. Min Act: -0.0001

Data Index: 143497 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1744. Min Act: -0.0001

Data Index: 334644 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1208785 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1653. Min Act: -0.0001

Data Index: 58728 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1355918 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1750. Min Act: -0.0001

Data Index: 296617 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1701. Min Act: -0.0001

Data Index: 538847 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1579. Min Act: -0.0001

Data Index: 637469 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1234818 (C4 (Web Text))

Max Activating Token Index: 942