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

Dataset: The Pile

Neuron 4658 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: 0.8836. Min Range: -0.8836

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1359517 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6214. Min Act: -0.0000

Data Index: 197294 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1143869 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1930817 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1276387 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5658. Min Act: -0.0000

Data Index: 673154 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5553. Min Act: -0.0000

Data Index: 524496 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1493483 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1991525 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5511. Min Act: -0.0000

Data Index: 732704 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1483356 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1621565 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1246438 (The Pile)

Max Activating Token Index: 853

Text #13

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5079. Min Act: -0.0000

Data Index: 879485 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1123553 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1977503 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5014. Min Act: -0.0000

Data Index: 145541 (The Pile)

Max Activating Token Index: 588

Text #17

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5042. Min Act: -0.0000

Data Index: 973323 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5033. Min Act: -0.0000

Data Index: 526753 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1906846 (The Pile)

Max Activating Token Index: 695