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

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

Neuron 1542 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: 0.2746. Min Range: -0.2746

Max Act: 0.2746. Min Act: -0.0001

Data Index: 624417 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1414687 (Python Code)

Max Activating Token Index: 627

Text #2

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1793. Min Act: -0.0001

Data Index: 840844 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1082404 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1521. Min Act: -0.0000

Data Index: 707936 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1601. Min Act: -0.0001

Data Index: 691121 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1773. Min Act: -0.0001

Data Index: 1236661 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1697. Min Act: -0.0001

Data Index: 745964 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1522. Min Act: -0.0001

Data Index: 565966 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1198967 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1611. Min Act: -0.0001

Data Index: 392324 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1586. Min Act: -0.0001

Data Index: 758089 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1633. Min Act: -0.0000

Data Index: 838117 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1536501 (Python Code)

Max Activating Token Index: 779

Text #14

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1617. Min Act: -0.0000

Data Index: 293397 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1750. Min Act: -0.0000

Data Index: 921345 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1526. Min Act: -0.0001

Data Index: 357226 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1623. Min Act: -0.0001

Data Index: 753106 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1564. Min Act: -0.0001

Data Index: 780915 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1351. Min Act: -0.0001

Data Index: 895181 (C4 (Web Text))

Max Activating Token Index: 307