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

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

Neuron 3399 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: 0.0669. Min Range: -0.0669

Max Act: 0.0669. Min Act: -0.0003

Data Index: 405754 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0667. Min Act: -0.0003

Data Index: 825019 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0617. Min Act: -0.0002

Data Index: 670075 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0638. Min Act: -0.0003

Data Index: 756594 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0616. Min Act: -0.0003

Data Index: 249640 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0615. Min Act: -0.0003

Data Index: 712104 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0619. Min Act: -0.0003

Data Index: 946681 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1193879 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0599. Min Act: -0.0003

Data Index: 807732 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0572. Min Act: -0.0003

Data Index: 739871 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1261561 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0593. Min Act: -0.0003

Data Index: 174855 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0600. Min Act: -0.0002

Data Index: 985828 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0582. Min Act: -0.0002

Data Index: 151753 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1112676 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0576. Min Act: -0.0003

Data Index: 694416 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1251680 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0596. Min Act: -0.0002

Data Index: 291879 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0569. Min Act: -0.0003

Data Index: 388039 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0550. Min Act: -0.0002

Data Index: 248577 (C4 (Web Text))

Max Activating Token Index: 283