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

Dataset: The Pile

Neuron 1982 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: 1.0928. Min Range: -1.0928

Max Act: 1.0928. Min Act: -0.0000

Data Index: 771690 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1742559 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1274148 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.7542. Min Act: -0.0000

Data Index: 833053 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1626596 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.7229. Min Act: -0.0000

Data Index: 801972 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1557440 (The Pile)

Max Activating Token Index: 379

Text #7

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6459. Min Act: -0.0000

Data Index: 454561 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1654015 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6308. Min Act: -0.0000

Data Index: 874346 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6566. Min Act: -0.0000

Data Index: 399279 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1740331 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6604. Min Act: -0.0000

Data Index: 729051 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1056122 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6556. Min Act: -0.0000

Data Index: 899528 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1385931 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6539. Min Act: -0.0000

Data Index: 463185 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1473804 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1566451 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.5956. Min Act: -0.0000

Data Index: 411871 (The Pile)

Max Activating Token Index: 774