Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 64 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0805. Min Act: -0.0002

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1230786 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1229121 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0625. Min Act: -0.0002

Data Index: 868540 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0630. Min Act: -0.0002

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1200989 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0662. Min Act: -0.0002

Data Index: 862180 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0659. Min Act: -0.0002

Data Index: 408197 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0675. Min Act: -0.0002

Data Index: 638114 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0775. Min Act: -0.0002

Data Index: 854834 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1177003 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0583. Min Act: -0.0002

Data Index: 829223 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0563. Min Act: -0.0002

Data Index: 408740 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0566. Min Act: -0.0002

Data Index: 514815 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0594. Min Act: -0.0002

Data Index: 246178 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0636. Min Act: -0.0002

Data Index: 965303 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0628. Min Act: -0.0002

Data Index: 584469 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0572. Min Act: -0.0002

Data Index: 121429 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0535. Min Act: -0.0002

Data Index: 222755 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0536. Min Act: -0.0002

Data Index: 824606 (C4 (Web Text))

Max Activating Token Index: 880