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

Dataset: The Pile

Neuron 4774 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: 0.1911. Min Range: -0.1911

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1195952 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1897669 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1804225 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1052690 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1133103 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1450. Min Act: -0.0000

Data Index: 697154 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1278165 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1497. Min Act: -0.0000

Data Index: 1476507 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1065691 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1255034 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1917459 (The Pile)

Max Activating Token Index: 583

Text #11

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1438773 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1435. Min Act: -0.0000

Data Index: 112744 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1465632 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1304. Min Act: -0.0000

Data Index: 931563 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1128. Min Act: -0.0000

Data Index: 139565 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1413135 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1912828 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1259. Min Act: -0.0000

Data Index: 189849 (The Pile)

Max Activating Token Index: 720

Text #19

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1311. Min Act: -0.0000

Data Index: 171320 (The Pile)

Max Activating Token Index: 747