Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 742 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0750. Min Range: -4.0750

Max Act: 4.0750. Min Act: -0.0000

Data Index: 297269 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.9434. Min Act: -0.0001

Data Index: 1077659 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 4.0750. Min Range: -4.0750

Max Act: 3.0985. Min Act: -0.0000

Data Index: 602208 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.9357. Min Act: -0.0001

Data Index: 1062504 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.6425. Min Act: -0.0000

Data Index: 1315341 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.6933. Min Act: -0.0001

Data Index: 431543 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.5890. Min Act: -0.0000

Data Index: 1063039 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.5782. Min Act: -0.0000

Data Index: 421336 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.7219. Min Act: -0.0001

Data Index: 1307397 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.4245. Min Act: -0.0000

Data Index: 653701 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.6604. Min Act: -0.0000

Data Index: 609189 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.5336. Min Act: -0.0000

Data Index: 523041 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.3612. Min Act: -0.0001

Data Index: 179098 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.3541. Min Act: -0.0000

Data Index: 106900 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.5873. Min Act: -0.0001

Data Index: 500424 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.5563. Min Act: -0.0000

Data Index: 1201908 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.5625. Min Act: -0.0001

Data Index: 221508 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.5397. Min Act: -0.0000

Data Index: 222174 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.5476. Min Act: -0.0001

Data Index: 289857 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 4.0750. Min Range: -4.0750

Max Act: 2.3954. Min Act: -0.0000

Data Index: 250408 (C4 (Web Text))

Max Activating Token Index: 558