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

Dataset: The Pile

Neuron 4821 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1194. Min Act: -0.0000

Data Index: 366360 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1342366 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1383395 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0840. Min Act: -0.0000

Data Index: 371202 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0977. Min Act: -0.0000

Data Index: 677039 (The Pile)

Max Activating Token Index: 37

Text #5

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1423467 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0915. Min Act: -0.0000

Data Index: 467744 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1136301 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0840. Min Act: -0.0000

Data Index: 279537 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1245951 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1978322 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1785322 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1239673 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0889. Min Act: -0.0000

Data Index: 982971 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0720. Min Act: -0.0000

Data Index: 719846 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0696. Min Act: -0.0000

Data Index: 552873 (The Pile)

Max Activating Token Index: 9

Text #16

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0667. Min Act: -0.0000

Data Index: 982603 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0595. Min Act: -0.0000

Data Index: 1151151 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1669079 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0599. Min Act: -0.0000

Data Index: 197231 (The Pile)

Max Activating Token Index: 329