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

Dataset: The Pile

Neuron 1410 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.5352. Min Act: -0.0000

Data Index: 597069 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.6090. Min Act: -0.0000

Data Index: 1640095 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.4604. Min Act: -0.0000

Data Index: 900799 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.2709. Min Act: -0.0000

Data Index: 1421989 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.1868. Min Act: 0.0001

Data Index: 107966 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.1387. Min Act: -0.0000

Data Index: 765288 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.0638. Min Act: -0.0000

Data Index: 162833 (The Pile)

Max Activating Token Index: 882

Text #7

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1351844 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1055028 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.0439. Min Act: -0.0000

Data Index: 634901 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.0504. Min Act: -0.0000

Data Index: 792116 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.0053. Min Act: -0.0000

Data Index: 733710 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.0082. Min Act: -0.0000

Data Index: 327449 (The Pile)

Max Activating Token Index: 550

Text #13

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1545782 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 1.6090. Min Range: -1.6090

Max Act: 0.9981. Min Act: -0.0000

Data Index: 424382 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.0309. Min Act: -0.0000

Data Index: 391808 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1131190 (The Pile)

Max Activating Token Index: 575

Text #17

Max Range: 1.6090. Min Range: -1.6090

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1942215 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 1.6090. Min Range: -1.6090

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1492412 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 1.6090. Min Range: -1.6090

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1540842 (The Pile)

Max Activating Token Index: 223