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

Dataset: The Pile

Neuron 2506 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1014340 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1191250 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1490366 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1463571 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1857578 (The Pile)

Max Activating Token Index: 808

Text #5

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1474274 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1517850 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5971. Min Act: -0.0000

Data Index: 78035 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1473974 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5889. Min Act: -0.0000

Data Index: 697561 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1671185 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1520448 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5887. Min Act: -0.0000

Data Index: 110808 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1328754 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6012. Min Act: -0.0000

Data Index: 599931 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1252697 (The Pile)

Max Activating Token Index: 590

Text #16

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5687. Min Act: -0.0000

Data Index: 475245 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1486332 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1704156 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1451778 (The Pile)

Max Activating Token Index: 580