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

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

Neuron 3837 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1528605 (Python Code)

Max Activating Token Index: 569

Text #1

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0930. Min Act: -0.0001

Data Index: 140940 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1459302 (Python Code)

Max Activating Token Index: 728

Text #3

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1547240 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0874. Min Act: -0.0001

Data Index: 952612 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1226474 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1283687 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1383378 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0788. Min Act: -0.0001

Data Index: 710106 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0773. Min Act: -0.0001

Data Index: 296881 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0774. Min Act: -0.0001

Data Index: 867518 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1649190 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0856. Min Act: -0.0001

Data Index: 888687 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0790. Min Act: -0.0001

Data Index: 899177 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1652954 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1417882 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1545524 (Python Code)

Max Activating Token Index: 421

Text #17

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1646806 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1233929 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1316016 (C4 (Web Text))

Max Activating Token Index: 734