Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 232 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0002

Data Index: 208571 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0770. Min Act: -0.0003

Data Index: 930645 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0765. Min Act: -0.0001

Data Index: 263550 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0739. Min Act: -0.0003

Data Index: 487839 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0714. Min Act: -0.0003

Data Index: 976454 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0731. Min Act: 0.0000

Data Index: 67511 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0715. Min Act: -0.0002

Data Index: 926787 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0721. Min Act: -0.0003

Data Index: 677500 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0697. Min Act: -0.0003

Data Index: 1255717 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0704. Min Act: -0.0003

Data Index: 789340 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0680. Min Act: -0.0003

Data Index: 993982 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0681. Min Act: -0.0001

Data Index: 103202 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0683. Min Act: -0.0003

Data Index: 1084208 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0651. Min Act: -0.0001

Data Index: 136841 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0675. Min Act: -0.0003

Data Index: 486812 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1023213 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0653. Min Act: -0.0002

Data Index: 421601 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0663. Min Act: 0.0000

Data Index: 622573 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0670. Min Act: -0.0003

Data Index: 153236 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0658. Min Act: -0.0003

Data Index: 743073 (C4 (Web Text))

Max Activating Token Index: 787