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

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

Neuron 4319 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: 0.5389. Min Range: -0.5389

Max Act: 0.5284. Min Act: -0.0000

Data Index: 725814 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.5114. Min Act: -0.0000

Data Index: 315215 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.5389. Min Act: -0.0000

Data Index: 765371 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4617. Min Act: -0.0000

Data Index: 348654 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4805. Min Act: -0.0000

Data Index: 663478 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4905. Min Act: -0.0000

Data Index: 590498 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4867. Min Act: -0.0000

Data Index: 370479 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4550. Min Act: -0.0000

Data Index: 278721 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1111100 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4689. Min Act: -0.0000

Data Index: 878971 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1303976 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1203164 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1279327 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4715. Min Act: -0.0000

Data Index: 242277 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4370. Min Act: -0.0000

Data Index: 702287 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1243850 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1168697 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1242654 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1221845 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4379. Min Act: -0.0000

Data Index: 210946 (C4 (Web Text))

Max Activating Token Index: 896