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

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

Neuron 1674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6745. Min Act: -0.0000

Data Index: 256831 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6657. Min Act: -0.0000

Data Index: 35641 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6156. Min Act: -0.0000

Data Index: 975663 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1071073 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6546. Min Act: -0.0000

Data Index: 523292 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6510. Min Act: -0.0000

Data Index: 961903 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6439. Min Act: -0.0000

Data Index: 246725 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1020063 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6203. Min Act: -0.0000

Data Index: 997370 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6300. Min Act: -0.0000

Data Index: 610531 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6694. Min Act: -0.0000

Data Index: 159998 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1357916 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5834. Min Act: -0.0000

Data Index: 313345 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5816. Min Act: -0.0000

Data Index: 130538 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6376. Min Act: -0.0000

Data Index: 900967 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5962. Min Act: -0.0000

Data Index: 697863 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6166. Min Act: -0.0000

Data Index: 303041 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6358. Min Act: -0.0000

Data Index: 828589 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6306. Min Act: -0.0000

Data Index: 576357 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5902. Min Act: -0.0000

Data Index: 549891 (C4 (Web Text))

Max Activating Token Index: 470