Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2146 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.7872. Min Act: -0.0001

Data Index: 1085963 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.7624. Min Act: -0.0000

Data Index: 323528 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.7579. Min Act: -0.0000

Data Index: 548857 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.7041. Min Act: -0.0000

Data Index: 375260 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.7625. Min Act: -0.0000

Data Index: 226376 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.7195. Min Act: -0.0000

Data Index: 873940 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6781. Min Act: -0.0000

Data Index: 782891 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.7040. Min Act: -0.0000

Data Index: 697830 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1123049 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6753. Min Act: -0.0000

Data Index: 163350 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6219. Min Act: -0.0000

Data Index: 525589 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1174103 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5709. Min Act: -0.0000

Data Index: 380583 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6487. Min Act: -0.0001

Data Index: 149517 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6045. Min Act: -0.0001

Data Index: 1044275 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6193. Min Act: -0.0000

Data Index: 896966 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6044. Min Act: -0.0001

Data Index: 186779 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6184. Min Act: -0.0001

Data Index: 379155 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6311. Min Act: -0.0000

Data Index: 580715 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5804. Min Act: -0.0000

Data Index: 690034 (C4 (Web Text))

Max Activating Token Index: 899