Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 106 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0005

Data Index: 570710 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0810. Min Act: -0.0005

Data Index: 16995 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0738. Min Act: -0.0005

Data Index: 1283582 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0698. Min Act: -0.0005

Data Index: 791845 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0697. Min Act: -0.0005

Data Index: 1041368 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0684. Min Act: -0.0005

Data Index: 48990 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0666. Min Act: -0.0005

Data Index: 949919 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0649. Min Act: -0.0005

Data Index: 106598 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0657. Min Act: -0.0005

Data Index: 1262076 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0655. Min Act: -0.0005

Data Index: 137 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0628. Min Act: -0.0005

Data Index: 1327095 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0631. Min Act: -0.0005

Data Index: 875937 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0600. Min Act: -0.0005

Data Index: 519805 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0603. Min Act: -0.0005

Data Index: 252071 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0610. Min Act: -0.0005

Data Index: 1217542 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0623. Min Act: -0.0005

Data Index: 1269097 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0590. Min Act: -0.0005

Data Index: 518297 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0586. Min Act: -0.0005

Data Index: 729294 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0597. Min Act: -0.0005

Data Index: 1247515 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0583. Min Act: -0.0005

Data Index: 851564 (C4 (Web Text))

Max Activating Token Index: 239