Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4077 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.2827. Min Act: -0.0001

Data Index: 769462 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.2500. Min Act: -0.0001

Data Index: 814734 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.2354. Min Act: -0.0001

Data Index: 336647 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.2062. Min Act: -0.0001

Data Index: 321184 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.2035. Min Act: -0.0001

Data Index: 952044 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1836. Min Act: -0.0001

Data Index: 580509 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1635. Min Act: -0.0001

Data Index: 993416 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1833. Min Act: -0.0001

Data Index: 77218 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1741. Min Act: -0.0001

Data Index: 263993 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1481. Min Act: -0.0001

Data Index: 50661 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1195007 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1794. Min Act: -0.0001

Data Index: 582546 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1636. Min Act: -0.0001

Data Index: 579093 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1530. Min Act: -0.0001

Data Index: 685755 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1627. Min Act: -0.0001

Data Index: 954092 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1048104 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1447. Min Act: -0.0001

Data Index: 925032 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1667. Min Act: -0.0001

Data Index: 203390 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1473. Min Act: -0.0001

Data Index: 163810 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.2827. Min Range: -0.2827

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1355823 (C4 (Web Text))

Max Activating Token Index: 101