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

Dataset: The Pile

Neuron 3201 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0943. Min Act: 0.0000

Data Index: 1752545 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1829578 (The Pile)

Max Activating Token Index: 838

Text #2

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0874. Min Act: 0.0000

Data Index: 1226110 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1198875 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1982122 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0863. Min Act: -0.0000

Data Index: 580794 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0859. Min Act: -0.0000

Data Index: 917984 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1974243 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1906159 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0815. Min Act: -0.0000

Data Index: 369388 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0824. Min Act: -0.0000

Data Index: 511482 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0821. Min Act: 0.0000

Data Index: 975942 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1243011 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1971482 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1122052 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1059808 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1985705 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0791. Min Act: 0.0000

Data Index: 923772 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0791. Min Act: -0.0000

Data Index: 213222 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0771. Min Act: 0.0000

Data Index: 1651382 (The Pile)

Max Activating Token Index: 483