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

Dataset: The Pile

Neuron 2433 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: 0.2793. Min Range: -0.2793

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1174034 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2394. Min Act: -0.0000

Data Index: 545086 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1720917 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1669. Min Act: -0.0000

Data Index: 577802 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1597. Min Act: -0.0000

Data Index: 783534 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1496. Min Act: -0.0000

Data Index: 861488 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1200506 (The Pile)

Max Activating Token Index: 436

Text #7

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1745959 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1447823 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1388. Min Act: -0.0000

Data Index: 469286 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1813920 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1202. Min Act: -0.0000

Data Index: 812833 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1466. Min Act: -0.0000

Data Index: 68099 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1455446 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1346. Min Act: -0.0000

Data Index: 771734 (The Pile)

Max Activating Token Index: 672

Text #15

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1287. Min Act: -0.0000

Data Index: 909796 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1337. Min Act: -0.0000

Data Index: 434093 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1318. Min Act: -0.0000

Data Index: 619787 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1604. Min Act: -0.0000

Data Index: 262209 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1371. Min Act: -0.0000

Data Index: 351985 (The Pile)

Max Activating Token Index: 642