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

Dataset: The Pile

Neuron 292 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: 0.7647. Min Range: -0.7647

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1770036 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1289962 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.7145. Min Act: -0.0000

Data Index: 478660 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6453. Min Act: -0.0000

Data Index: 252854 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.7172. Min Act: -0.0000

Data Index: 36517 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1957277 (The Pile)

Max Activating Token Index: 656

Text #6

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.7014. Min Act: -0.0000

Data Index: 982270 (The Pile)

Max Activating Token Index: 477

Text #7

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6441. Min Act: -0.0000

Data Index: 371677 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6848. Min Act: -0.0000

Data Index: 51877 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1797913 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6871. Min Act: -0.0000

Data Index: 102546 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1767035 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6503. Min Act: -0.0000

Data Index: 357091 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1178699 (The Pile)

Max Activating Token Index: 932

Text #14

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5982. Min Act: -0.0000

Data Index: 754515 (The Pile)

Max Activating Token Index: 338

Text #15

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1809550 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6518. Min Act: -0.0000

Data Index: 603304 (The Pile)

Max Activating Token Index: 910

Text #17

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1054859 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5940. Min Act: -0.0000

Data Index: 438551 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6115. Min Act: -0.0000

Data Index: 647610 (The Pile)

Max Activating Token Index: 976