Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1032 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1720. Min Act: -0.0002

Data Index: 1190512 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1633. Min Act: -0.0002

Data Index: 8039 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1627. Min Act: -0.0002

Data Index: 352605 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1620. Min Act: -0.0002

Data Index: 225353 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1538. Min Act: -0.0002

Data Index: 1009848 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1447. Min Act: -0.0002

Data Index: 1199454 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1420. Min Act: -0.0002

Data Index: 1186679 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1527. Min Act: -0.0002

Data Index: 592157 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1472. Min Act: -0.0002

Data Index: 1088341 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1477. Min Act: -0.0002

Data Index: 309785 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1466. Min Act: -0.0002

Data Index: 273264 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1474. Min Act: -0.0002

Data Index: 996730 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1464. Min Act: -0.0002

Data Index: 1121270 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1461. Min Act: -0.0001

Data Index: 836529 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1401. Min Act: -0.0001

Data Index: 710330 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1442. Min Act: -0.0002

Data Index: 1230401 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1435. Min Act: -0.0002

Data Index: 679868 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1434. Min Act: -0.0002

Data Index: 661881 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1432. Min Act: -0.0002

Data Index: 150294 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1444. Min Act: -0.0001

Data Index: 720399 (C4 (Web Text))

Max Activating Token Index: 449