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

Dataset: The Pile

Neuron 1395 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: 0.8693. Min Range: -0.8693

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1862433 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8118. Min Act: -0.0000

Data Index: 812261 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1882079 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1388557 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6712. Min Act: -0.0000

Data Index: 979374 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1747078 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6488. Min Act: -0.0000

Data Index: 855444 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1446911 (The Pile)

Max Activating Token Index: 318

Text #8

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6180. Min Act: -0.0000

Data Index: 134097 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6371. Min Act: -0.0000

Data Index: 745531 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1777967 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1128845 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1372293 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1618523 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6495. Min Act: -0.0000

Data Index: 199565 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1100976 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1916119 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6121. Min Act: -0.0000

Data Index: 223162 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1251655 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6178. Min Act: -0.0000

Data Index: 312629 (The Pile)

Max Activating Token Index: 81