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

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

Neuron 1165 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: 0.6511. Min Range: -0.6511

Max Act: 0.6511. Min Act: -0.0000

Data Index: 723179 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.6339. Min Act: -0.0000

Data Index: 925293 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.6352. Min Act: -0.0000

Data Index: 484696 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.6123. Min Act: -0.0000

Data Index: 132297 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1246552 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5792. Min Act: -0.0000

Data Index: 357313 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5762. Min Act: -0.0000

Data Index: 252535 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1259674 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1148176 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5403. Min Act: -0.0000

Data Index: 339624 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1171149 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5280. Min Act: -0.0000

Data Index: 912997 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5841. Min Act: -0.0000

Data Index: 944619 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5551. Min Act: -0.0000

Data Index: 357545 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1266129 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1205733 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.4908. Min Act: -0.0000

Data Index: 315674 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5437. Min Act: -0.0000

Data Index: 457072 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.4987. Min Act: -0.0000

Data Index: 173022 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.4986. Min Act: -0.0000

Data Index: 329841 (C4 (Web Text))

Max Activating Token Index: 761