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

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

Neuron 3030 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2523. Min Act: -0.0000

Data Index: 726259 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2349. Min Act: -0.0000

Data Index: 771354 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1863. Min Act: -0.0000

Data Index: 109737 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1897. Min Act: -0.0000

Data Index: 479512 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1829. Min Act: -0.0000

Data Index: 915737 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1160280 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1865. Min Act: -0.0000

Data Index: 561622 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1923. Min Act: -0.0000

Data Index: 302001 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1777. Min Act: -0.0000

Data Index: 798591 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1666. Min Act: -0.0000

Data Index: 624889 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1773. Min Act: -0.0000

Data Index: 166211 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1597. Min Act: -0.0000

Data Index: 371790 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1653. Min Act: -0.0000

Data Index: 210079 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1584. Min Act: -0.0000

Data Index: 309901 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1615. Min Act: -0.0000

Data Index: 394320 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1147260 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1637. Min Act: -0.0000

Data Index: 654559 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1506. Min Act: -0.0000

Data Index: 567594 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1143358 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1481. Min Act: -0.0000

Data Index: 724269 (C4 (Web Text))

Max Activating Token Index: 506