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

Dataset: The Pile

Neuron 5086 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.7392. Min Act: -0.0000

Data Index: 312430 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1744219 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1563508 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1028219 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1812260 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1663298 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1906201 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1926321 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5953. Min Act: -0.0000

Data Index: 24021 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1176139 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1855849 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1777495 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5387. Min Act: -0.0000

Data Index: 655199 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5219. Min Act: -0.0000

Data Index: 310612 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1008420 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1207703 (The Pile)

Max Activating Token Index: 665

Text #16

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5333. Min Act: -0.0000

Data Index: 251929 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1948341 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1260019 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5516. Min Act: -0.0000

Data Index: 52009 (The Pile)

Max Activating Token Index: 822