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

Dataset: The Pile

Neuron 3775 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: 3.9017. Min Range: -3.9017

Max Act: 3.9017. Min Act: -0.0000

Data Index: 1219017 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.6896. Min Act: -0.0000

Data Index: 1275147 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.2111. Min Act: -0.0000

Data Index: 1763817 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3259. Min Act: -0.0000

Data Index: 65751 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.1739. Min Act: -0.0000

Data Index: 1546568 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.2490. Min Act: -0.0000

Data Index: 1453823 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.2194. Min Act: -0.0000

Data Index: 1701522 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.0287. Min Act: -0.0000

Data Index: 1184942 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.0896. Min Act: 0.0000

Data Index: 633457 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.0455. Min Act: -0.0000

Data Index: 416916 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 3.9017. Min Range: -3.9017

Max Act: 2.8934. Min Act: -0.0000

Data Index: 1134500 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.0021. Min Act: -0.0000

Data Index: 789153 (The Pile)

Max Activating Token Index: 92

Text #12

Max Range: 3.9017. Min Range: -3.9017

Max Act: 2.8545. Min Act: -0.0000

Data Index: 245895 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 3.9017. Min Range: -3.9017

Max Act: 2.7254. Min Act: -0.0000

Data Index: 1334931 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 3.9017. Min Range: -3.9017

Max Act: 2.9260. Min Act: -0.0000

Data Index: 1510356 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 3.9017. Min Range: -3.9017

Max Act: 2.9127. Min Act: -0.0000

Data Index: 492046 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 3.9017. Min Range: -3.9017

Max Act: 2.9116. Min Act: -0.0000

Data Index: 328551 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 3.9017. Min Range: -3.9017

Max Act: 2.7439. Min Act: -0.0000

Data Index: 1239736 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 3.9017. Min Range: -3.9017

Max Act: 2.8727. Min Act: -0.0000

Data Index: 1346560 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 3.9017. Min Range: -3.9017

Max Act: 2.7068. Min Act: -0.0000

Data Index: 1765090 (The Pile)

Max Activating Token Index: 608