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

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

Neuron 3935 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1219479 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1033. Min Act: -0.0000

Data Index: 277049 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0907. Min Act: -0.0000

Data Index: 630829 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0869. Min Act: -0.0000

Data Index: 944679 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1270173 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0797. Min Act: -0.0000

Data Index: 590821 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0820. Min Act: -0.0000

Data Index: 513402 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0743. Min Act: -0.0000

Data Index: 238572 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0711. Min Act: -0.0000

Data Index: 693358 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1253608 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1149906 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0741. Min Act: -0.0000

Data Index: 902448 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0686. Min Act: -0.0000

Data Index: 280333 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0686. Min Act: -0.0000

Data Index: 808937 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0641. Min Act: -0.0000

Data Index: 760343 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1052802 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0611. Min Act: -0.0000

Data Index: 390035 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0652. Min Act: -0.0000

Data Index: 156669 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1114903 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1018387 (C4 (Web Text))

Max Activating Token Index: 6