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

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

Neuron 2355 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1836. Min Act: -0.0000

Data Index: 657550 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1112495 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1790. Min Act: -0.0001

Data Index: 292538 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1136291 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1832. Min Act: -0.0000

Data Index: 539106 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1838. Min Act: -0.0000

Data Index: 883136 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1787. Min Act: -0.0000

Data Index: 273477 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1672. Min Act: -0.0000

Data Index: 809406 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1785. Min Act: -0.0000

Data Index: 42792 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1850. Min Act: -0.0001

Data Index: 825057 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1650. Min Act: -0.0000

Data Index: 445191 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1707. Min Act: -0.0001

Data Index: 716724 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1690. Min Act: -0.0000

Data Index: 29117 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1739. Min Act: -0.0000

Data Index: 67921 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1744. Min Act: -0.0000

Data Index: 424516 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1253339 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1790. Min Act: -0.0001

Data Index: 5834 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1786. Min Act: -0.0000

Data Index: 890398 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1260982 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1578. Min Act: -0.0000

Data Index: 903367 (C4 (Web Text))

Max Activating Token Index: 665