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

Dataset: The Pile

Neuron 1427 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.1008. Min Act: -0.0000

Data Index: 399960 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9960. Min Act: -0.0000

Data Index: 610345 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.0167. Min Act: -0.0000

Data Index: 918769 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1168935 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.0130. Min Act: -0.0000

Data Index: 883281 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1612632 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.0347. Min Act: -0.0000

Data Index: 570870 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1364513 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1848415 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9638. Min Act: -0.0000

Data Index: 587323 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.0066. Min Act: -0.0000

Data Index: 1595782 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 1.1008. Min Range: -1.1008

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1038801 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9741. Min Act: -0.0000

Data Index: 197361 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1714036 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9523. Min Act: -0.0000

Data Index: 36819 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9941. Min Act: -0.0000

Data Index: 741308 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1364041 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9222. Min Act: -0.0000

Data Index: 884170 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1818462 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.1008. Min Range: -1.1008

Max Act: 0.9123. Min Act: -0.0000

Data Index: 175568 (The Pile)

Max Activating Token Index: 357