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

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

Neuron 4275 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1393. Min Act: -0.0001

Data Index: 247376 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1096. Min Act: -0.0001

Data Index: 460735 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0945. Min Act: -0.0001

Data Index: 285598 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0874. Min Act: -0.0001

Data Index: 958045 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0836. Min Act: -0.0001

Data Index: 376318 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0738. Min Act: -0.0001

Data Index: 22320 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0817. Min Act: -0.0001

Data Index: 874634 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0888. Min Act: -0.0001

Data Index: 980376 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0828. Min Act: -0.0001

Data Index: 41738 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1176647 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0829. Min Act: -0.0001

Data Index: 645827 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0748. Min Act: -0.0001

Data Index: 8614 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0748. Min Act: -0.0001

Data Index: 546171 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0770. Min Act: -0.0001

Data Index: 738212 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0793. Min Act: -0.0001

Data Index: 293579 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1221380 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0726. Min Act: -0.0001

Data Index: 552511 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1017016 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0623. Min Act: -0.0001

Data Index: 515540 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0705. Min Act: -0.0001

Data Index: 804642 (C4 (Web Text))

Max Activating Token Index: 159