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

Dataset: The Pile

Neuron 641 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: 1.7912. Min Range: -1.7912

Max Act: 1.7912. Min Act: -0.0000

Data Index: 313610 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.7021. Min Act: -0.0000

Data Index: 263714 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5793. Min Act: -0.0000

Data Index: 1245039 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5119. Min Act: -0.0000

Data Index: 1292168 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5483. Min Act: -0.0000

Data Index: 968145 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5504. Min Act: -0.0000

Data Index: 371392 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5849. Min Act: -0.0000

Data Index: 1614016 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5930. Min Act: -0.0000

Data Index: 689607 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5154. Min Act: -0.0000

Data Index: 1205117 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4948. Min Act: -0.0000

Data Index: 1898294 (The Pile)

Max Activating Token Index: 435

Text #10

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4581. Min Act: -0.0000

Data Index: 1250270 (The Pile)

Max Activating Token Index: 840

Text #11

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1255241 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5100. Min Act: -0.0000

Data Index: 706654 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4123. Min Act: -0.0000

Data Index: 407318 (The Pile)

Max Activating Token Index: 698

Text #14

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.3656. Min Act: -0.0000

Data Index: 1020361 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4919. Min Act: -0.0000

Data Index: 1607724 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1403434 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4304. Min Act: -0.0000

Data Index: 989770 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1639526 (The Pile)

Max Activating Token Index: 437

Text #19

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1634659 (The Pile)

Max Activating Token Index: 9