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

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

Neuron 5111 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1181245 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0792. Min Act: -0.0001

Data Index: 778920 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0687. Min Act: -0.0001

Data Index: 131149 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0711. Min Act: -0.0001

Data Index: 387987 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0681. Min Act: -0.0001

Data Index: 3739 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0655. Min Act: -0.0002

Data Index: 787106 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0684. Min Act: -0.0001

Data Index: 907584 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0686. Min Act: -0.0001

Data Index: 699060 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0693. Min Act: -0.0001

Data Index: 26572 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0672. Min Act: -0.0001

Data Index: 349785 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0642. Min Act: -0.0001

Data Index: 921198 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0636. Min Act: -0.0001

Data Index: 279096 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1281901 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0617. Min Act: -0.0001

Data Index: 973980 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0581. Min Act: -0.0001

Data Index: 766353 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1173964 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1243111 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1194344 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0628. Min Act: -0.0001

Data Index: 620800 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1069860 (C4 (Web Text))

Max Activating Token Index: 127