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

Dataset: The Pile

Neuron 2018 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: 0.6054. Min Range: -0.6054

Max Act: 0.6054. Min Act: -0.0000

Data Index: 781497 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1729559 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1875854 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5286. Min Act: -0.0000

Data Index: 179305 (The Pile)

Max Activating Token Index: 809

Text #4

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1464052 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1714091 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1585327 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1429645 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4960. Min Act: -0.0000

Data Index: 905693 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5002. Min Act: -0.0000

Data Index: 501859 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1944892 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4514. Min Act: -0.0000

Data Index: 810589 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1210710 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4752. Min Act: -0.0000

Data Index: 184060 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1320218 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1229495 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4678. Min Act: -0.0000

Data Index: 717928 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4347. Min Act: -0.0000

Data Index: 616345 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1049734 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4434. Min Act: -0.0000

Data Index: 13949 (The Pile)

Max Activating Token Index: 655