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

Dataset: The Pile

Neuron 1778 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: 1.0245. Min Range: -1.0245

Max Act: 1.0245. Min Act: -0.0000

Data Index: 558520 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1877228 (The Pile)

Max Activating Token Index: 34

Text #2

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.7488. Min Act: -0.0000

Data Index: 709665 (The Pile)

Max Activating Token Index: 729

Text #3

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8053. Min Act: -0.0000

Data Index: 660764 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1268686 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6908. Min Act: -0.0000

Data Index: 57670 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6160. Min Act: -0.0000

Data Index: 450329 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6604. Min Act: -0.0000

Data Index: 86389 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6889. Min Act: -0.0000

Data Index: 962311 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1111025 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6655. Min Act: -0.0000

Data Index: 234844 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6619. Min Act: -0.0000

Data Index: 423648 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6129. Min Act: -0.0000

Data Index: 653422 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1475772 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1557231 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6468. Min Act: -0.0000

Data Index: 479523 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6435. Min Act: -0.0000

Data Index: 101536 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6407. Min Act: -0.0000

Data Index: 560002 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6620. Min Act: -0.0000

Data Index: 793410 (The Pile)

Max Activating Token Index: 1015

Text #19

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6630. Min Act: -0.0000

Data Index: 117079 (The Pile)

Max Activating Token Index: 802