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

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

Neuron 3148 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: 1.1252. Min Range: -1.1252

Max Act: 1.1252. Min Act: 0.0000

Data Index: 701980 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.9937. Min Act: -0.0000

Data Index: 785667 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 1.1252. Min Range: -1.1252

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1330329 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.9186. Min Act: 0.0000

Data Index: 839956 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.8675. Min Act: 0.0000

Data Index: 1252430 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1307318 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.8322. Min Act: -0.0000

Data Index: 690336 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.8616. Min Act: 0.0000

Data Index: 1244652 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.7989. Min Act: 0.0000

Data Index: 457054 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.7271. Min Act: 0.0000

Data Index: 376527 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.7018. Min Act: -0.0000

Data Index: 653415 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1075771 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.6659. Min Act: -0.0000

Data Index: 873701 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.6850. Min Act: 0.0000

Data Index: 1178961 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.6750. Min Act: -0.0000

Data Index: 723835 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.6681. Min Act: -0.0000

Data Index: 369253 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.6224. Min Act: -0.0000

Data Index: 778532 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1027283 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.6351. Min Act: -0.0000

Data Index: 243408 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.1252. Min Range: -1.1252

Max Act: 0.5704. Min Act: -0.0000

Data Index: 880015 (C4 (Web Text))

Max Activating Token Index: 22