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

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

Neuron 3200 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4628. Min Act: -0.0000

Data Index: 732808 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4266. Min Act: -0.0000

Data Index: 779266 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3849. Min Act: -0.0000

Data Index: 1080015 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2776. Min Act: -0.0000

Data Index: 431361 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2754. Min Act: -0.0000

Data Index: 546469 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1215909 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2742. Min Act: -0.0000

Data Index: 988492 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2695. Min Act: -0.0000

Data Index: 1024876 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2676. Min Act: -0.0000

Data Index: 968390 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1812. Min Act: -0.0000

Data Index: 378531 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1672. Min Act: -0.0000

Data Index: 853212 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1270537 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2355. Min Act: -0.0000

Data Index: 814352 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2978. Min Act: -0.0000

Data Index: 62234 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2027. Min Act: -0.0000

Data Index: 922962 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1982. Min Act: -0.0000

Data Index: 631953 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2734. Min Act: -0.0000

Data Index: 496927 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1930. Min Act: -0.0000

Data Index: 848973 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2658. Min Act: -0.0000

Data Index: 304031 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1095. Min Act: -0.0000

Data Index: 196502 (C4 (Web Text))

Max Activating Token Index: 143