Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2641 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.6528. Min Act: -0.0000

Data Index: 217220 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1194971 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.5266. Min Act: -0.0000

Data Index: 1422898 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.3238. Min Act: -0.0000

Data Index: 421843 (The Pile)

Max Activating Token Index: 137

Text #4

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.3221. Min Act: -0.0000

Data Index: 349291 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.2363. Min Act: -0.0000

Data Index: 92326 (The Pile)

Max Activating Token Index: 637

Text #6

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.2199. Min Act: -0.0000

Data Index: 97579 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.2664. Min Act: -0.0000

Data Index: 1856903 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.1126. Min Act: -0.0000

Data Index: 460496 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.2322. Min Act: -0.0000

Data Index: 368788 (The Pile)

Max Activating Token Index: 891

Text #10

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.1921. Min Act: -0.0000

Data Index: 513024 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0952. Min Act: -0.0000

Data Index: 1926334 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1216605 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0640. Min Act: -0.0000

Data Index: 1066840 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1306868 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1692958 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1322207 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1210401 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 1.6898. Min Range: -1.6898

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1610991 (The Pile)

Max Activating Token Index: 587

Text #19

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0150. Min Act: -0.0000

Data Index: 86009 (The Pile)

Max Activating Token Index: 410