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

Dataset: The Pile

Neuron 2613 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: 1.1009. Min Range: -1.1009

Max Act: 1.1009. Min Act: -0.0000

Data Index: 386484 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 1.1009. Min Range: -1.1009

Max Act: 1.0953. Min Act: -0.0000

Data Index: 37398 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9896. Min Act: -0.0000

Data Index: 845061 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1160911 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1573019 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1287088 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9170. Min Act: -0.0000

Data Index: 666526 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9051. Min Act: -0.0000

Data Index: 32913 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1413604 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1957644 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1002856 (The Pile)

Max Activating Token Index: 679

Text #11

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9511. Min Act: -0.0000

Data Index: 420702 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1775151 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9100. Min Act: -0.0000

Data Index: 245141 (The Pile)

Max Activating Token Index: 431

Text #14

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1235916 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1782325 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.8865. Min Act: -0.0000

Data Index: 353562 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1839836 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.8860. Min Act: -0.0000

Data Index: 1950095 (The Pile)

Max Activating Token Index: 872

Text #19

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.8556. Min Act: -0.0000

Data Index: 503664 (The Pile)

Max Activating Token Index: 228