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

Dataset: The Pile

Neuron 2403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1705715 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1771. Min Act: -0.0000

Data Index: 955196 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1465. Min Act: -0.0000

Data Index: 753361 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1724569 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1158961 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1175. Min Act: -0.0000

Data Index: 280506 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1251. Min Act: -0.0000

Data Index: 658231 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1601902 (The Pile)

Max Activating Token Index: 319

Text #8

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1990898 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1551693 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1129. Min Act: -0.0000

Data Index: 173699 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1215. Min Act: -0.0000

Data Index: 33420 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1114. Min Act: -0.0000

Data Index: 362281 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1487272 (The Pile)

Max Activating Token Index: 412

Text #14

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1167. Min Act: -0.0000

Data Index: 323091 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1328350 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1126. Min Act: -0.0000

Data Index: 973069 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1263. Min Act: -0.0000

Data Index: 510336 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1150. Min Act: -0.0000

Data Index: 711298 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1039. Min Act: -0.0000

Data Index: 9517 (The Pile)

Max Activating Token Index: 440