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

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

Neuron 20 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.6494. Min Act: -0.0000

Data Index: 364697 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.2631. Min Act: -0.0000

Data Index: 1284297 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.2618. Min Act: -0.0000

Data Index: 380253 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.2001. Min Act: -0.0000

Data Index: 1076896 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 3.6494. Min Range: -3.6494

Max Act: 3.0328. Min Act: -0.0000

Data Index: 276259 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.9782. Min Act: -0.0000

Data Index: 763496 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.9687. Min Act: -0.0000

Data Index: 435765 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.9491. Min Act: -0.0000

Data Index: 522431 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.9523. Min Act: -0.0000

Data Index: 994135 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.7778. Min Act: -0.0000

Data Index: 470100 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.8855. Min Act: -0.0000

Data Index: 545060 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.8882. Min Act: -0.0000

Data Index: 204002 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.7295. Min Act: -0.0000

Data Index: 173540 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.8617. Min Act: -0.0000

Data Index: 1047758 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.8434. Min Act: -0.0000

Data Index: 1128455 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.7872. Min Act: -0.0000

Data Index: 1106688 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.5274. Min Act: -0.0000

Data Index: 1339749 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.7855. Min Act: -0.0000

Data Index: 561236 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.9047. Min Act: -0.0000

Data Index: 1184489 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 3.6494. Min Range: -3.6494

Max Act: 2.6398. Min Act: -0.0000

Data Index: 1357369 (C4 (Web Text))

Max Activating Token Index: 863