Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3383 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0001

Data Index: 873701 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0712. Min Act: -0.0001

Data Index: 523411 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0635. Min Act: -0.0000

Data Index: 469627 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1330372 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0636. Min Act: -0.0000

Data Index: 684136 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1323765 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0620. Min Act: -0.0001

Data Index: 685190 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0586. Min Act: -0.0000

Data Index: 803828 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0597. Min Act: -0.0001

Data Index: 396614 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0600. Min Act: -0.0001

Data Index: 505910 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1171200 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0528. Min Act: -0.0001

Data Index: 501218 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1098527 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0518. Min Act: -0.0001

Data Index: 779724 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1162283 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0547. Min Act: -0.0001

Data Index: 541810 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0545. Min Act: -0.0000

Data Index: 874 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0563. Min Act: -0.0001

Data Index: 418706 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0541. Min Act: -0.0001

Data Index: 518897 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0521. Min Act: -0.0001

Data Index: 901794 (C4 (Web Text))

Max Activating Token Index: 136