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

Dataset: The Pile

Neuron 3991 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: 1.2196. Min Range: -1.2196

Max Act: 1.2196. Min Act: -0.0000

Data Index: 975763 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1386068 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 1.2196. Min Range: -1.2196

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1912393 (The Pile)

Max Activating Token Index: 903

Text #3

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9417. Min Act: -0.0000

Data Index: 236185 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8483. Min Act: -0.0000

Data Index: 49165 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8614. Min Act: -0.0000

Data Index: 285147 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 1.2196. Min Range: -1.2196

Max Act: 1.0264. Min Act: -0.0000

Data Index: 158386 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9015. Min Act: -0.0000

Data Index: 597251 (The Pile)

Max Activating Token Index: 754

Text #8

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9048. Min Act: -0.0000

Data Index: 38378 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1757486 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1421274 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1305347 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9095. Min Act: -0.0000

Data Index: 269814 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1661917 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1352121 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1487734 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7958. Min Act: -0.0000

Data Index: 190275 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1393112 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1018038 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9387. Min Act: -0.0001

Data Index: 1803289 (The Pile)

Max Activating Token Index: 934