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

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

Neuron 2654 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: 1.2754. Min Range: -1.2754

Max Act: 1.2618. Min Act: -0.0000

Data Index: 190800 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.2754. Min Act: -0.0000

Data Index: 966463 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.0770. Min Act: -0.0000

Data Index: 216681 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.0944. Min Act: -0.0000

Data Index: 452830 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.0769. Min Act: -0.0000

Data Index: 557263 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.9421. Min Act: -0.0000

Data Index: 490063 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8702. Min Act: -0.0000

Data Index: 833447 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8321. Min Act: -0.0000

Data Index: 174726 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8348. Min Act: -0.0000

Data Index: 395177 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.7874. Min Act: -0.0000

Data Index: 35837 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.7856. Min Act: -0.0000

Data Index: 887160 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1264009 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1321634 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8284. Min Act: -0.0000

Data Index: 55776 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.7859. Min Act: -0.0000

Data Index: 434175 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8185. Min Act: -0.0000

Data Index: 505000 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1270649 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.7282. Min Act: -0.0000

Data Index: 136025 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1274232 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1121935 (C4 (Web Text))

Max Activating Token Index: 840