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

Dataset: The Pile

Neuron 2358 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: 1.1828. Min Range: -1.1828

Max Act: 1.1828. Min Act: -0.0000

Data Index: 993863 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.1120. Min Act: -0.0000

Data Index: 185206 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0639. Min Act: -0.0000

Data Index: 532850 (The Pile)

Max Activating Token Index: 796

Text #3

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0468. Min Act: -0.0000

Data Index: 551664 (The Pile)

Max Activating Token Index: 574

Text #4

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1648160 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1432984 (The Pile)

Max Activating Token Index: 727

Text #6

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9657. Min Act: -0.0000

Data Index: 45323 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0267. Min Act: -0.0000

Data Index: 1799122 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1937507 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1631813 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1394953 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0070. Min Act: -0.0000

Data Index: 616133 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9928. Min Act: -0.0000

Data Index: 150689 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9549. Min Act: -0.0000

Data Index: 750536 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9505. Min Act: -0.0000

Data Index: 427433 (The Pile)

Max Activating Token Index: 941

Text #15

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0484. Min Act: -0.0000

Data Index: 352176 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0073. Min Act: -0.0000

Data Index: 667010 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9154. Min Act: -0.0000

Data Index: 92603 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9438. Min Act: -0.0000

Data Index: 379395 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1010040 (The Pile)

Max Activating Token Index: 414