Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 281 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0002

Data Index: 798802 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0857. Min Act: -0.0002

Data Index: 393127 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0818. Min Act: -0.0002

Data Index: 589820 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0764. Min Act: -0.0002

Data Index: 13957 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1063905 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0741. Min Act: -0.0002

Data Index: 991245 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0736. Min Act: -0.0002

Data Index: 592644 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0729. Min Act: -0.0002

Data Index: 415976 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0705. Min Act: -0.0002

Data Index: 769959 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0678. Min Act: -0.0002

Data Index: 720104 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0684. Min Act: -0.0002

Data Index: 317283 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1122451 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0692. Min Act: -0.0002

Data Index: 886902 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0666. Min Act: -0.0002

Data Index: 775278 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0674. Min Act: -0.0002

Data Index: 229354 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0665. Min Act: -0.0002

Data Index: 650977 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0686. Min Act: -0.0002

Data Index: 534132 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0686. Min Act: -0.0002

Data Index: 332775 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0678. Min Act: -0.0002

Data Index: 116590 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1210540 (C4 (Web Text))

Max Activating Token Index: 104