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

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

Neuron 3737 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1283702 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1116008 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1072395 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1005235 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0631. Min Act: -0.0002

Data Index: 700870 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0676. Min Act: -0.0002

Data Index: 988757 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1164700 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1335455 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0623. Min Act: -0.0002

Data Index: 40299 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0637. Min Act: -0.0002

Data Index: 227678 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0620. Min Act: -0.0002

Data Index: 327862 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1326024 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0664. Min Act: -0.0002

Data Index: 603208 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0631. Min Act: -0.0002

Data Index: 427720 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0582. Min Act: -0.0002

Data Index: 193591 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1160573 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1129429 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0567. Min Act: -0.0002

Data Index: 148329 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1359494 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0553. Min Act: -0.0002

Data Index: 907909 (C4 (Web Text))

Max Activating Token Index: 298