Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5423 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2597. Min Act: -0.0002

Data Index: 1010123 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2050. Min Act: -0.0002

Data Index: 704660 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1852. Min Act: -0.0002

Data Index: 119730 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1910. Min Act: -0.0002

Data Index: 385724 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1864. Min Act: -0.0002

Data Index: 29114 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1655. Min Act: -0.0002

Data Index: 767055 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1664. Min Act: -0.0002

Data Index: 93542 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1691. Min Act: -0.0002

Data Index: 1130698 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1762. Min Act: -0.0002

Data Index: 366917 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1671. Min Act: -0.0002

Data Index: 854063 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1499. Min Act: -0.0002

Data Index: 89997 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1602. Min Act: -0.0002

Data Index: 461743 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1597. Min Act: -0.0002

Data Index: 604561 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1572. Min Act: -0.0002

Data Index: 1223006 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1509. Min Act: -0.0002

Data Index: 677791 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1568. Min Act: -0.0002

Data Index: 792452 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1561. Min Act: -0.0002

Data Index: 1131247 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1616. Min Act: -0.0002

Data Index: 544743 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1675. Min Act: -0.0002

Data Index: 1281861 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1573. Min Act: -0.0002

Data Index: 646035 (C4 (Web Text))

Max Activating Token Index: 441