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

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

Neuron 1613 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: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1549389 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1385458 (Python Code)

Max Activating Token Index: 519

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1608830 (Python Code)

Max Activating Token Index: 692

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1447424 (Python Code)

Max Activating Token Index: 943

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1399461 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1524903 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1517939 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1607612 (Python Code)

Max Activating Token Index: 464

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1530135 (Python Code)

Max Activating Token Index: 254

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1398734 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1395018 (Python Code)

Max Activating Token Index: 507

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1451917 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1462743 (Python Code)

Max Activating Token Index: 833

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1401881 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1440946 (Python Code)

Max Activating Token Index: 314

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1402766 (Python Code)

Max Activating Token Index: 881

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1598401 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1570058 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1440617 (Python Code)

Max Activating Token Index: 803

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1442972 (Python Code)

Max Activating Token Index: 879