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

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

Neuron 81 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.3495. Min Act: -0.0001

Data Index: 504201 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2824. Min Act: -0.0001

Data Index: 778808 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2531. Min Act: -0.0001

Data Index: 318884 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2189. Min Act: -0.0001

Data Index: 838156 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1831. Min Act: -0.0001

Data Index: 700098 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1828. Min Act: -0.0001

Data Index: 22592 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1036629 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1750. Min Act: -0.0001

Data Index: 97891 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1815. Min Act: -0.0001

Data Index: 673875 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1685. Min Act: -0.0001

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1612. Min Act: -0.0001

Data Index: 37388 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1108473 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1668. Min Act: -0.0001

Data Index: 431320 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1466. Min Act: -0.0001

Data Index: 634055 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1268443 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1524. Min Act: -0.0001

Data Index: 998444 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1553. Min Act: -0.0001

Data Index: 970370 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1524. Min Act: -0.0001

Data Index: 640907 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1509. Min Act: -0.0001

Data Index: 713248 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.1482. Min Act: -0.0001

Data Index: 585915 (C4 (Web Text))

Max Activating Token Index: 79