Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5853 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1579992 (Python Code)

Max Activating Token Index: 38

Text #1

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1578811 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1377833 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1544935 (Python Code)

Max Activating Token Index: 55

Text #4

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1512311 (Python Code)

Max Activating Token Index: 178

Text #5

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1475699 (Python Code)

Max Activating Token Index: 111

Text #6

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1631460 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1462695 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1363366 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1562170 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1577813 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1520056 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1425191 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1648874 (Python Code)

Max Activating Token Index: 624

Text #14

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1488927 (Python Code)

Max Activating Token Index: 682

Text #15

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1442721 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1391201 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1507238 (Python Code)

Max Activating Token Index: 351

Text #18

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1589503 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1625197 (Python Code)

Max Activating Token Index: 84