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

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

Neuron 1115 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: 2.1401. Min Range: -2.1401

Max Act: 2.1401. Min Act: -0.0000

Data Index: 820870 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 2.1401. Min Range: -2.1401

Max Act: 2.1288. Min Act: -0.0000

Data Index: 1021195 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.9054. Min Act: -0.0000

Data Index: 687660 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.8806. Min Act: -0.0000

Data Index: 980873 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.7624. Min Act: -0.0000

Data Index: 1112686 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.7856. Min Act: -0.0000

Data Index: 1049132 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.6974. Min Act: -0.0000

Data Index: 876522 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.7851. Min Act: -0.0000

Data Index: 1341089 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.7526. Min Act: -0.0000

Data Index: 395580 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.6492. Min Act: -0.0000

Data Index: 401475 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.7250. Min Act: -0.0000

Data Index: 991817 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.6156. Min Act: -0.0000

Data Index: 667843 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1346898 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.6403. Min Act: -0.0000

Data Index: 874319 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.5462. Min Act: -0.0000

Data Index: 503894 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.6074. Min Act: -0.0000

Data Index: 480870 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.6023. Min Act: -0.0000

Data Index: 341947 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.5840. Min Act: -0.0000

Data Index: 430151 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.6394. Min Act: -0.0000

Data Index: 658691 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 2.1401. Min Range: -2.1401

Max Act: 1.5491. Min Act: -0.0000

Data Index: 775872 (C4 (Web Text))

Max Activating Token Index: 933