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

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

Neuron 2891 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.5210. Min Act: -0.0000

Data Index: 241647 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2193. Min Act: -0.0000

Data Index: 439215 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2385. Min Act: -0.0000

Data Index: 938432 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2395. Min Act: 0.0000

Data Index: 545334 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1816. Min Act: -0.0000

Data Index: 5458 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1811. Min Act: -0.0000

Data Index: 522315 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1512. Min Act: -0.0000

Data Index: 505962 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1263. Min Act: 0.0000

Data Index: 636100 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0345. Min Act: 0.0000

Data Index: 898028 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1006914 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0826. Min Act: -0.0000

Data Index: 740347 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0072. Min Act: 0.0000

Data Index: 214749 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0063. Min Act: -0.0000

Data Index: 31061 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9393. Min Act: 0.0000

Data Index: 370261 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0592. Min Act: 0.0000

Data Index: 444244 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1200419 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1213985 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9753. Min Act: -0.0000

Data Index: 782342 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9127. Min Act: -0.0000

Data Index: 17879 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.8803. Min Act: -0.0000

Data Index: 603381 (C4 (Web Text))

Max Activating Token Index: 693