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

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

Neuron 2137 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1090546 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1727. Min Act: -0.0000

Data Index: 503081 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1581. Min Act: -0.0000

Data Index: 280115 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1303802 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1485027 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1568. Min Act: -0.0000

Data Index: 635337 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1620. Min Act: -0.0000

Data Index: 923993 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1381163 (Python Code)

Max Activating Token Index: 369

Text #8

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1422214 (Python Code)

Max Activating Token Index: 493

Text #9

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1504. Min Act: -0.0000

Data Index: 822232 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1111741 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1501. Min Act: -0.0000

Data Index: 436303 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1242185 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1471. Min Act: -0.0000

Data Index: 276589 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1352. Min Act: -0.0000

Data Index: 597083 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1433. Min Act: -0.0000

Data Index: 883154 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1295. Min Act: -0.0000

Data Index: 419209 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1590227 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1323. Min Act: -0.0000

Data Index: 701755 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1422. Min Act: -0.0000

Data Index: 22149 (C4 (Web Text))

Max Activating Token Index: 641