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

Dataset: The Pile

Neuron 2155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1225. Min Range: -1.1225

Max Act: 1.1164. Min Act: -0.0000

Data Index: 277259 (The Pile)

Max Activating Token Index: 951

Text #1

Max Range: 1.1225. Min Range: -1.1225

Max Act: 1.1225. Min Act: -0.0000

Data Index: 533009 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 1.1225. Min Range: -1.1225

Max Act: 1.0606. Min Act: -0.0000

Data Index: 1405446 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 1.1225. Min Range: -1.1225

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1832669 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 1.1225. Min Range: -1.1225

Max Act: 1.0616. Min Act: -0.0000

Data Index: 726807 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.9597. Min Act: -0.0000

Data Index: 769755 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1960864 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.9189. Min Act: -0.0000

Data Index: 702512 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.9320. Min Act: -0.0000

Data Index: 693250 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1796106 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.9546. Min Act: -0.0000

Data Index: 550546 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8232. Min Act: -0.0000

Data Index: 910782 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1803602 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1235986 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8356. Min Act: -0.0000

Data Index: 114323 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1124908 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8085. Min Act: -0.0000

Data Index: 825318 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1463962 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8441. Min Act: -0.0000

Data Index: 773740 (The Pile)

Max Activating Token Index: 119

Text #19

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.7830. Min Act: -0.0000

Data Index: 648625 (The Pile)

Max Activating Token Index: 411