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

Dataset: The Pile

Neuron 3325 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: 0.1788. Min Range: -0.1788

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1601232 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1680. Min Act: -0.0000

Data Index: 693181 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1539211 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1649. Min Act: -0.0000

Data Index: 27609 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1480. Min Act: -0.0000

Data Index: 655619 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1183282 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1565581 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1450. Min Act: -0.0000

Data Index: 865417 (The Pile)

Max Activating Token Index: 149

Text #8

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1207283 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1685468 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1430. Min Act: -0.0000

Data Index: 105543 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1375130 (The Pile)

Max Activating Token Index: 519

Text #12

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1479. Min Act: -0.0000

Data Index: 512452 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1352. Min Act: -0.0000

Data Index: 865446 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1179313 (The Pile)

Max Activating Token Index: 658

Text #15

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1823418 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1679417 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1469. Min Act: -0.0000

Data Index: 124990 (The Pile)

Max Activating Token Index: 306

Text #18

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1462644 (The Pile)

Max Activating Token Index: 691

Text #19

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1529789 (The Pile)

Max Activating Token Index: 364