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

Dataset: The Pile

Neuron 4800 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: 1.6389. Min Range: -1.6389

Max Act: 1.6389. Min Act: -0.0000

Data Index: 800764 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.3872. Min Act: -0.0000

Data Index: 1784439 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.3107. Min Act: -0.0001

Data Index: 1561031 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.2441. Min Act: -0.0000

Data Index: 964477 (The Pile)

Max Activating Token Index: 877

Text #4

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1522617 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.3900. Min Act: -0.0001

Data Index: 88253 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.1445. Min Act: -0.0000

Data Index: 926476 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.1833. Min Act: -0.0000

Data Index: 227700 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.1697. Min Act: -0.0000

Data Index: 1134594 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1207834 (The Pile)

Max Activating Token Index: 136

Text #10

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.1399. Min Act: -0.0000

Data Index: 345115 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.0836. Min Act: -0.0000

Data Index: 534398 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.0316. Min Act: -0.0000

Data Index: 68690 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.0401. Min Act: -0.0000

Data Index: 629112 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.0667. Min Act: -0.0000

Data Index: 138418 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 1.6389. Min Range: -1.6389

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1002426 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 1.6389. Min Range: -1.6389

Max Act: 0.9906. Min Act: -0.0000

Data Index: 33436 (The Pile)

Max Activating Token Index: 981

Text #17

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.1838. Min Act: -0.0000

Data Index: 118559 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.0793. Min Act: -0.0000

Data Index: 1592212 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 1.6389. Min Range: -1.6389

Max Act: 1.0419. Min Act: -0.0000

Data Index: 868620 (The Pile)

Max Activating Token Index: 298