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

Dataset: The Pile

Neuron 4435 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1934252 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1783335 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1998011 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1525241 (The Pile)

Max Activating Token Index: 692

Text #4

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1590. Min Act: -0.0000

Data Index: 338797 (The Pile)

Max Activating Token Index: 507

Text #5

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1309968 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1585. Min Act: -0.0000

Data Index: 150077 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1528. Min Act: -0.0000

Data Index: 168372 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1570. Min Act: -0.0000

Data Index: 534203 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1356. Min Act: -0.0000

Data Index: 44880 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1527028 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1447. Min Act: -0.0000

Data Index: 473291 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1450. Min Act: -0.0000

Data Index: 751974 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1378. Min Act: -0.0000

Data Index: 175348 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1513. Min Act: -0.0000

Data Index: 956593 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1355. Min Act: -0.0000

Data Index: 128327 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1343. Min Act: -0.0000

Data Index: 16989 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1376. Min Act: -0.0000

Data Index: 840818 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1300. Min Act: -0.0000

Data Index: 833456 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1060934 (The Pile)

Max Activating Token Index: 531