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

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

Neuron 1170 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.7492. Min Act: -0.0000

Data Index: 626221 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.8623. Min Act: -0.0000

Data Index: 1047411 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.6059. Min Act: -0.0000

Data Index: 950753 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.1256. Min Act: -0.0000

Data Index: 1282100 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.2099. Min Act: -0.0000

Data Index: 263936 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.2602. Min Act: -0.0000

Data Index: 446577 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.5719. Min Act: 0.0001

Data Index: 559950 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.7935. Min Act: 0.0001

Data Index: 71296 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.7304. Min Act: 0.0000

Data Index: 732018 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.5575. Min Act: -0.0000

Data Index: 429982 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.6654. Min Act: -0.0000

Data Index: 280502 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.5966. Min Act: -0.0000

Data Index: 1283460 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.6513. Min Act: -0.0000

Data Index: 1302312 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.5200. Min Act: -0.0000

Data Index: 822646 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.3418. Min Act: -0.0000

Data Index: 98993 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.3525. Min Act: -0.0000

Data Index: 515005 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.4114. Min Act: -0.0000

Data Index: 1251561 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.3725. Min Act: -0.0000

Data Index: 1214400 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.3594. Min Act: -0.0000

Data Index: 953027 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.3627. Min Act: 0.0000

Data Index: 533612 (C4 (Web Text))

Max Activating Token Index: 101