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

Dataset: The Pile

Neuron 386 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0178. Min Range: -1.0178

Max Act: 1.0178. Min Act: -0.0000

Data Index: 649895 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 1.0178. Min Range: -1.0178

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1317612 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1106937 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.9306. Min Act: -0.0000

Data Index: 379825 (The Pile)

Max Activating Token Index: 761

Text #4

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.9083. Min Act: -0.0000

Data Index: 441468 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8621. Min Act: -0.0000

Data Index: 701164 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8307. Min Act: -0.0000

Data Index: 608489 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8736. Min Act: -0.0000

Data Index: 835813 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8160. Min Act: -0.0000

Data Index: 25727 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8400. Min Act: -0.0000

Data Index: 426901 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1434301 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1879866 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1178242 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7773. Min Act: -0.0000

Data Index: 184813 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1569609 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1859940 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1721789 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8055. Min Act: -0.0000

Data Index: 409796 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1610673 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1557523 (The Pile)

Max Activating Token Index: 445