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

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

Neuron 3872 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0589. Min Range: -4.0589

Max Act: 4.0589. Min Act: -0.0000

Data Index: 590265 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 4.0589. Min Range: -4.0589

Max Act: 3.7796. Min Act: -0.0000

Data Index: 341672 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 4.0589. Min Range: -4.0589

Max Act: 3.0129. Min Act: -0.0000

Data Index: 301088 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.9859. Min Act: -0.0000

Data Index: 543812 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.8870. Min Act: -0.0000

Data Index: 924061 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.8291. Min Act: -0.0000

Data Index: 1206451 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.8989. Min Act: -0.0000

Data Index: 3007 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 4.0589. Min Range: -4.0589

Max Act: 3.0130. Min Act: -0.0000

Data Index: 767980 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.5907. Min Act: -0.0000

Data Index: 945387 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.9690. Min Act: -0.0000

Data Index: 529427 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.5168. Min Act: -0.0000

Data Index: 508319 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.6246. Min Act: -0.0000

Data Index: 569868 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.3738. Min Act: -0.0000

Data Index: 1124134 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.4617. Min Act: -0.0000

Data Index: 1335361 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.5244. Min Act: -0.0000

Data Index: 91615 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.5451. Min Act: -0.0000

Data Index: 1188197 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.6693. Min Act: -0.0000

Data Index: 164266 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.5447. Min Act: -0.0000

Data Index: 387041 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.4947. Min Act: -0.0000

Data Index: 1202135 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 4.0589. Min Range: -4.0589

Max Act: 2.6400. Min Act: -0.0000

Data Index: 14553 (C4 (Web Text))

Max Activating Token Index: 176