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

Dataset: The Pile

Neuron 2797 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.9215. Min Act: -0.0000

Data Index: 855330 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1935392 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1550840 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6067. Min Act: -0.0000

Data Index: 656607 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5779. Min Act: -0.0000

Data Index: 870858 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1968147 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5614. Min Act: -0.0000

Data Index: 957775 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1376053 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5278. Min Act: -0.0000

Data Index: 611719 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1556996 (The Pile)

Max Activating Token Index: 740

Text #10

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1020395 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1485331 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1437183 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1304396 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4841. Min Act: -0.0000

Data Index: 733136 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5031. Min Act: -0.0000

Data Index: 527625 (The Pile)

Max Activating Token Index: 454

Text #16

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1881331 (The Pile)

Max Activating Token Index: 787

Text #17

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1840748 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1664674 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1334293 (The Pile)

Max Activating Token Index: 558