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

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

Neuron 2688 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: 0.0612. Min Range: -0.0612

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1175730 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0002

Data Index: 851900 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1300991 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0538. Min Act: -0.0003

Data Index: 584002 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0511. Min Act: -0.0003

Data Index: 341736 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0507. Min Act: -0.0003

Data Index: 160371 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1193620 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0497. Min Act: -0.0003

Data Index: 701928 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1227333 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0486. Min Act: -0.0003

Data Index: 185825 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0476. Min Act: -0.0003

Data Index: 345960 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1114958 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0447. Min Act: -0.0003

Data Index: 781849 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0479. Min Act: -0.0003

Data Index: 401203 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0441. Min Act: -0.0003

Data Index: 897294 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0449. Min Act: -0.0003

Data Index: 84851 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0445. Min Act: -0.0003

Data Index: 671676 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0442. Min Act: -0.0003

Data Index: 413928 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1175411 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0426. Min Act: -0.0003

Data Index: 150650 (C4 (Web Text))

Max Activating Token Index: 699