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

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

Neuron 4117 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1734. Min Act: -0.0002

Data Index: 1629918 (Python Code)

Max Activating Token Index: 723

Text #1

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1594. Min Act: -0.0002

Data Index: 1434281 (Python Code)

Max Activating Token Index: 743

Text #2

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1778. Min Act: -0.0002

Data Index: 1485556 (Python Code)

Max Activating Token Index: 211

Text #3

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1625. Min Act: -0.0002

Data Index: 1534178 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1801. Min Act: -0.0002

Data Index: 1604080 (Python Code)

Max Activating Token Index: 654

Text #5

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1593. Min Act: -0.0002

Data Index: 1591311 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1779. Min Act: -0.0002

Data Index: 1460868 (Python Code)

Max Activating Token Index: 476

Text #7

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1510. Min Act: -0.0002

Data Index: 1646692 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1591. Min Act: -0.0002

Data Index: 1510218 (Python Code)

Max Activating Token Index: 224

Text #9

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1604. Min Act: -0.0002

Data Index: 1410349 (Python Code)

Max Activating Token Index: 584

Text #10

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1686. Min Act: -0.0002

Data Index: 1496123 (Python Code)

Max Activating Token Index: 743

Text #11

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1552. Min Act: -0.0002

Data Index: 1367403 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1632. Min Act: -0.0002

Data Index: 1482560 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1556. Min Act: -0.0002

Data Index: 1412927 (Python Code)

Max Activating Token Index: 121

Text #14

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1633. Min Act: -0.0002

Data Index: 1607763 (Python Code)

Max Activating Token Index: 433

Text #15

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1547. Min Act: -0.0002

Data Index: 1511285 (Python Code)

Max Activating Token Index: 411

Text #16

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1606. Min Act: -0.0002

Data Index: 1387133 (Python Code)

Max Activating Token Index: 605

Text #17

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1605. Min Act: -0.0002

Data Index: 1564280 (Python Code)

Max Activating Token Index: 441

Text #18

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1553. Min Act: -0.0002

Data Index: 1447875 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1567. Min Act: -0.0002

Data Index: 1447954 (Python Code)

Max Activating Token Index: 779