Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2728 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0243. Min Range: -1.0243

Max Act: 1.0243. Min Act: 0.0000

Data Index: 1252766 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1894527 (The Pile)

Max Activating Token Index: 434

Text #2

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7725. Min Act: -0.0000

Data Index: 364170 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1798575 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7609. Min Act: -0.0000

Data Index: 957005 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7301. Min Act: -0.0000

Data Index: 619492 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7428. Min Act: 0.0001

Data Index: 467904 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7643. Min Act: 0.0000

Data Index: 1783326 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7368. Min Act: -0.0000

Data Index: 138495 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1808079 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7160. Min Act: -0.0000

Data Index: 797341 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1898326 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1965909 (The Pile)

Max Activating Token Index: 676

Text #13

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1453192 (The Pile)

Max Activating Token Index: 322

Text #14

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1442292 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6782. Min Act: 0.0000

Data Index: 1565143 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6781. Min Act: -0.0000

Data Index: 821793 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6333. Min Act: 0.0000

Data Index: 1570693 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6643. Min Act: -0.0000

Data Index: 369229 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1851337 (The Pile)

Max Activating Token Index: 371