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

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

Neuron 10 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1278846 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0698. Min Act: -0.0002

Data Index: 541969 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1126059 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0629. Min Act: -0.0002

Data Index: 589320 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0590. Min Act: -0.0002

Data Index: 546354 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0590. Min Act: -0.0002

Data Index: 862623 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0624. Min Act: -0.0002

Data Index: 271546 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0619. Min Act: -0.0002

Data Index: 941452 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0572. Min Act: -0.0001

Data Index: 927017 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0528. Min Act: -0.0001

Data Index: 516937 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1293602 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0559. Min Act: -0.0001

Data Index: 950442 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0560. Min Act: -0.0002

Data Index: 190179 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0570. Min Act: -0.0001

Data Index: 572840 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0566. Min Act: -0.0002

Data Index: 889521 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1146856 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1225704 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0569. Min Act: -0.0002

Data Index: 251808 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0514. Min Act: -0.0002

Data Index: 63969 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0491. Min Act: -0.0001

Data Index: 420629 (C4 (Web Text))

Max Activating Token Index: 868