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

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

Neuron 3645 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: 1.1376. Min Range: -1.1376

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1281049 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0479. Min Act: -0.0000

Data Index: 764947 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.1376. Min Act: -0.0000

Data Index: 245281 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0693. Min Act: -0.0000

Data Index: 964461 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0623. Min Act: -0.0000

Data Index: 166779 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0390. Min Act: -0.0000

Data Index: 351208 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9864. Min Act: -0.0000

Data Index: 86920 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9807. Min Act: -0.0000

Data Index: 714067 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9709. Min Act: -0.0000

Data Index: 970837 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9344. Min Act: -0.0000

Data Index: 790813 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1144351 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9680. Min Act: -0.0000

Data Index: 822589 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.8790. Min Act: -0.0000

Data Index: 526261 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9363. Min Act: -0.0000

Data Index: 607135 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9222. Min Act: -0.0000

Data Index: 591212 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1177001 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9049. Min Act: -0.0000

Data Index: 696594 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.8996. Min Act: -0.0000

Data Index: 566179 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9227. Min Act: -0.0000

Data Index: 529934 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9530. Min Act: -0.0000

Data Index: 948217 (C4 (Web Text))

Max Activating Token Index: 848