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

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

Neuron 1624 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: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0002

Data Index: 630316 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1430997 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0696. Min Act: -0.0002

Data Index: 399012 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0698. Min Act: -0.0002

Data Index: 72165 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1554396 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0705. Min Act: -0.0002

Data Index: 203227 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0675. Min Act: -0.0002

Data Index: 843537 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1379000 (Python Code)

Max Activating Token Index: 768

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0621. Min Act: -0.0002

Data Index: 654493 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1374382 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0609. Min Act: -0.0002

Data Index: 531085 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0650. Min Act: -0.0002

Data Index: 878474 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0603. Min Act: -0.0002

Data Index: 992417 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1111153 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1475543 (Python Code)

Max Activating Token Index: 805

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0588. Min Act: -0.0002

Data Index: 805879 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0561. Min Act: -0.0002

Data Index: 398565 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0544. Min Act: -0.0002

Data Index: 942851 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0593. Min Act: -0.0002

Data Index: 418132 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0582. Min Act: -0.0002

Data Index: 685465 (C4 (Web Text))

Max Activating Token Index: 142