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

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

Neuron 3871 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0003

Data Index: 1145843 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0792. Min Act: -0.0003

Data Index: 425951 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1127375 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0830. Min Act: -0.0002

Data Index: 479807 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0782. Min Act: -0.0003

Data Index: 1252617 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1158903 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0777. Min Act: -0.0002

Data Index: 801412 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0777. Min Act: -0.0003

Data Index: 103478 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0789. Min Act: -0.0002

Data Index: 237104 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0774. Min Act: -0.0003

Data Index: 1013953 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0767. Min Act: -0.0003

Data Index: 537969 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0770. Min Act: -0.0003

Data Index: 106507 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0733. Min Act: -0.0003

Data Index: 699 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0744. Min Act: -0.0003

Data Index: 446507 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0718. Min Act: -0.0003

Data Index: 42546 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0769. Min Act: -0.0003

Data Index: 1120321 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0699. Min Act: -0.0003

Data Index: 229748 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0749. Min Act: -0.0003

Data Index: 630527 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0762. Min Act: -0.0003

Data Index: 391276 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0746. Min Act: -0.0003

Data Index: 369263 (C4 (Web Text))

Max Activating Token Index: 220