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

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

Neuron 315 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: 0.0878. Min Range: -0.0878

Max Act: 0.0873. Min Act: -0.0003

Data Index: 386534 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0873. Min Act: -0.0004

Data Index: 347500 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0003

Data Index: 1604565 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0810. Min Act: -0.0003

Data Index: 291707 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1612898 (Python Code)

Max Activating Token Index: 836

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0746. Min Act: -0.0003

Data Index: 55349 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0762. Min Act: -0.0003

Data Index: 821375 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0749. Min Act: -0.0004

Data Index: 774527 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0767. Min Act: -0.0004

Data Index: 75115 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1314242 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0655. Min Act: -0.0004

Data Index: 609722 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0701. Min Act: -0.0002

Data Index: 91342 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0688. Min Act: -0.0003

Data Index: 107991 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0663. Min Act: -0.0003

Data Index: 753611 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0644. Min Act: -0.0004

Data Index: 406968 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0632. Min Act: -0.0002

Data Index: 727549 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1265353 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0606. Min Act: -0.0003

Data Index: 789627 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0623. Min Act: -0.0004

Data Index: 1020361 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0599. Min Act: -0.0003

Data Index: 798324 (C4 (Web Text))

Max Activating Token Index: 825