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

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

Neuron 2981 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: 0.0876. Min Range: -0.0876

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1395968 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1606759 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1428232 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1524413 (Python Code)

Max Activating Token Index: 768

Text #4

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1384458 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1418506 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1510837 (Python Code)

Max Activating Token Index: 207

Text #7

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1428820 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1526853 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1472134 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1509845 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1387951 (Python Code)

Max Activating Token Index: 320

Text #12

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1381568 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1405823 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1370088 (Python Code)

Max Activating Token Index: 386

Text #15

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1548621 (Python Code)

Max Activating Token Index: 797

Text #16

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1639037 (Python Code)

Max Activating Token Index: 33

Text #17

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1571519 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1585978 (Python Code)

Max Activating Token Index: 678

Text #19

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1391971 (Python Code)

Max Activating Token Index: 164