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

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

Neuron 660 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0560. Min Range: -1.0560

Max Act: 1.0560. Min Act: -0.0000

Data Index: 740610 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9905. Min Act: 0.0000

Data Index: 543747 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1054167 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 1.0560. Min Range: -1.0560

Max Act: 1.0301. Min Act: 0.0000

Data Index: 1128198 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.0560. Min Range: -1.0560

Max Act: 1.0041. Min Act: -0.0000

Data Index: 42359 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9962. Min Act: -0.0000

Data Index: 804256 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9885. Min Act: -0.0000

Data Index: 191994 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 1.0560. Min Range: -1.0560

Max Act: 1.0087. Min Act: -0.0000

Data Index: 1291829 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9256. Min Act: -0.0000

Data Index: 274784 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9738. Min Act: -0.0000

Data Index: 50193 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9322. Min Act: 0.0000

Data Index: 928916 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9634. Min Act: 0.0001

Data Index: 412946 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9191. Min Act: 0.0001

Data Index: 647574 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9122. Min Act: 0.0000

Data Index: 831826 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1133296 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9164. Min Act: -0.0000

Data Index: 74883 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8861. Min Act: -0.0000

Data Index: 377330 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8162. Min Act: -0.0000

Data Index: 948484 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8585. Min Act: 0.0000

Data Index: 1052518 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1336342 (C4 (Web Text))

Max Activating Token Index: 540