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

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

Neuron 2992 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: 2.1632. Min Range: -2.1632

Max Act: 2.1632. Min Act: -0.0000

Data Index: 171944 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 2.1632. Min Range: -2.1632

Max Act: 2.0642. Min Act: -0.0000

Data Index: 703031 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 2.1632. Min Range: -2.1632

Max Act: 2.1216. Min Act: -0.0000

Data Index: 313662 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 2.1632. Min Range: -2.1632

Max Act: 2.0927. Min Act: -0.0000

Data Index: 165040 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.9914. Min Act: -0.0000

Data Index: 1143377 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 2.1632. Min Range: -2.1632

Max Act: 2.0015. Min Act: -0.0000

Data Index: 492233 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 2.1632. Min Range: -2.1632

Max Act: 2.0363. Min Act: 0.0001

Data Index: 1063353 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.8444. Min Act: 0.0001

Data Index: 819523 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.9001. Min Act: -0.0000

Data Index: 135150 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.7770. Min Act: -0.0000

Data Index: 1261404 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.7510. Min Act: -0.0000

Data Index: 871569 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.7526. Min Act: -0.0000

Data Index: 719703 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.8302. Min Act: -0.0000

Data Index: 21285 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.8168. Min Act: -0.0000

Data Index: 592569 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.6868. Min Act: -0.0000

Data Index: 29387 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.7812. Min Act: -0.0000

Data Index: 86745 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.7539. Min Act: 0.0000

Data Index: 837038 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.7492. Min Act: -0.0000

Data Index: 17857 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.8446. Min Act: -0.0000

Data Index: 1276495 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.7304. Min Act: -0.0000

Data Index: 1054287 (C4 (Web Text))

Max Activating Token Index: 375