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

Dataset: The Pile

Neuron 895 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1317452 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1476777 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1644420 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1136. Min Act: -0.0000

Data Index: 740357 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0847. Min Act: -0.0000

Data Index: 731023 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1013330 (The Pile)

Max Activating Token Index: 743

Text #6

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0989. Min Act: -0.0000

Data Index: 424214 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0963. Min Act: -0.0000

Data Index: 100559 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1037323 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1582940 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1092413 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0872. Min Act: -0.0000

Data Index: 306443 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0963. Min Act: -0.0000

Data Index: 450245 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0916. Min Act: -0.0000

Data Index: 570176 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1515768 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1678492 (The Pile)

Max Activating Token Index: 359

Text #16

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0885. Min Act: -0.0000

Data Index: 941213 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0849. Min Act: -0.0000

Data Index: 155109 (The Pile)

Max Activating Token Index: 690

Text #18

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0879. Min Act: -0.0000

Data Index: 971470 (The Pile)

Max Activating Token Index: 619

Text #19

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1050693 (The Pile)

Max Activating Token Index: 862