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

Dataset: The Pile

Neuron 3821 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0141. Min Range: -1.0141

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1164127 (The Pile)

Max Activating Token Index: 357

Text #1

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1174863 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1929906 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8971. Min Act: -0.0000

Data Index: 105047 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7513. Min Act: -0.0000

Data Index: 197434 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.5936. Min Act: -0.0000

Data Index: 359774 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7797. Min Act: -0.0000

Data Index: 49002 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7357. Min Act: -0.0000

Data Index: 914944 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.6999. Min Act: -0.0000

Data Index: 239092 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7139. Min Act: -0.0000

Data Index: 739214 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1251691 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.6680. Min Act: 0.0000

Data Index: 687363 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1954147 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.5931. Min Act: -0.0000

Data Index: 360312 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.5863. Min Act: -0.0000

Data Index: 170879 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.5459. Min Act: -0.0000

Data Index: 868260 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.6370. Min Act: 0.0000

Data Index: 1866341 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1702628 (The Pile)

Max Activating Token Index: 978

Text #18

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1171886 (The Pile)

Max Activating Token Index: 669

Text #19

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.5440. Min Act: -0.0000

Data Index: 210759 (The Pile)

Max Activating Token Index: 651