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

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

Neuron 872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.7266. Min Act: -0.0000

Data Index: 223773 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1221645 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.6518. Min Act: -0.0000

Data Index: 507388 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.6216. Min Act: -0.0000

Data Index: 921926 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5755. Min Act: -0.0000

Data Index: 316937 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5629. Min Act: -0.0000

Data Index: 653038 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1235251 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5778. Min Act: -0.0000

Data Index: 72582 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5723. Min Act: -0.0000

Data Index: 950135 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5690. Min Act: -0.0000

Data Index: 848919 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5730. Min Act: -0.0000

Data Index: 240117 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5668. Min Act: -0.0000

Data Index: 950754 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5674. Min Act: -0.0000

Data Index: 729721 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1043698 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5373. Min Act: -0.0000

Data Index: 260447 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5404. Min Act: -0.0000

Data Index: 808839 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5336. Min Act: -0.0000

Data Index: 395402 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5329. Min Act: 0.0001

Data Index: 352373 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5444. Min Act: -0.0000

Data Index: 123917 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1132877 (C4 (Web Text))

Max Activating Token Index: 326