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

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

Neuron 3816 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3436. Min Act: -0.0003

Data Index: 1047757 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3239. Min Act: -0.0003

Data Index: 344867 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3187. Min Act: -0.0002

Data Index: 169420 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3111. Min Act: -0.0002

Data Index: 874761 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3105. Min Act: -0.0002

Data Index: 640368 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2853. Min Act: -0.0003

Data Index: 118451 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2815. Min Act: -0.0003

Data Index: 512632 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2786. Min Act: -0.0003

Data Index: 357984 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2762. Min Act: -0.0003

Data Index: 857673 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2737. Min Act: -0.0002

Data Index: 60469 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2718. Min Act: -0.0003

Data Index: 451286 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2718. Min Act: -0.0002

Data Index: 1229908 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2713. Min Act: -0.0003

Data Index: 783661 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2698. Min Act: -0.0002

Data Index: 1045727 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2655. Min Act: -0.0003

Data Index: 548843 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2664. Min Act: -0.0003

Data Index: 907912 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2631. Min Act: -0.0002

Data Index: 1012416 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2612. Min Act: -0.0003

Data Index: 1156603 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2604. Min Act: -0.0003

Data Index: 541681 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2594. Min Act: -0.0002

Data Index: 660649 (C4 (Web Text))

Max Activating Token Index: 218