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

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

Neuron 5556 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.7824. Min Act: -0.0000

Data Index: 19612 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.8665. Min Act: -0.0001

Data Index: 1027850 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.7787. Min Act: -0.0001

Data Index: 92373 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.7420. Min Act: -0.0001

Data Index: 1085134 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.8235. Min Act: -0.0001

Data Index: 1288756 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.8052. Min Act: -0.0001

Data Index: 1144488 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.8235. Min Act: -0.0001

Data Index: 776487 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.6778. Min Act: -0.0001

Data Index: 210500 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.6855. Min Act: -0.0001

Data Index: 761786 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.5449. Min Act: -0.0001

Data Index: 1093806 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.6269. Min Act: -0.0001

Data Index: 136266 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.6183. Min Act: -0.0001

Data Index: 1312802 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.6115. Min Act: -0.0001

Data Index: 1308639 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.5611. Min Act: -0.0001

Data Index: 890989 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.5463. Min Act: -0.0001

Data Index: 697829 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.4986. Min Act: -0.0000

Data Index: 271421 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.5896. Min Act: -0.0001

Data Index: 866524 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.5318. Min Act: -0.0001

Data Index: 1223393 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.4742. Min Act: -0.0001

Data Index: 299783 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.5649. Min Act: -0.0001

Data Index: 759633 (C4 (Web Text))

Max Activating Token Index: 465