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

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

Neuron 3342 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5809. Min Range: -1.5809

Max Act: 1.5809. Min Act: -0.0000

Data Index: 990372 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.5809. Min Range: -1.5809

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1039402 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.5809. Min Range: -1.5809

Max Act: 1.1876. Min Act: -0.0000

Data Index: 175738 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.5809. Min Range: -1.5809

Max Act: 1.0677. Min Act: -0.0000

Data Index: 805253 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.5809. Min Range: -1.5809

Max Act: 1.1888. Min Act: -0.0000

Data Index: 487580 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.5809. Min Range: -1.5809

Max Act: 1.1239. Min Act: -0.0000

Data Index: 251672 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 1.5809. Min Range: -1.5809

Max Act: 1.0215. Min Act: -0.0000

Data Index: 403730 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1054761 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.9824. Min Act: -0.0000

Data Index: 859863 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.9434. Min Act: -0.0000

Data Index: 553683 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.9444. Min Act: -0.0000

Data Index: 23282 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1078370 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.9767. Min Act: -0.0000

Data Index: 255618 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.8835. Min Act: -0.0000

Data Index: 26206 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1344926 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.8789. Min Act: -0.0000

Data Index: 592857 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.8570. Min Act: -0.0000

Data Index: 663745 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1178586 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1285481 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.5809. Min Range: -1.5809

Max Act: 0.9198. Min Act: -0.0000

Data Index: 835386 (C4 (Web Text))

Max Activating Token Index: 511