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

Dataset: The Pile

Neuron 1829 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.8924. Min Range: -4.8924

Max Act: 4.7617. Min Act: -0.0000

Data Index: 1461625 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 4.8924. Min Range: -4.8924

Max Act: 4.5381. Min Act: -0.0000

Data Index: 1463169 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 4.8924. Min Range: -4.8924

Max Act: 4.8924. Min Act: -0.0000

Data Index: 1389312 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 4.8924. Min Range: -4.8924

Max Act: 4.3812. Min Act: -0.0000

Data Index: 241877 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 4.8924. Min Range: -4.8924

Max Act: 4.1492. Min Act: -0.0000

Data Index: 35633 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 4.8924. Min Range: -4.8924

Max Act: 4.1316. Min Act: -0.0000

Data Index: 698434 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.6468. Min Act: -0.0000

Data Index: 538033 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 4.8924. Min Range: -4.8924

Max Act: 4.0057. Min Act: -0.0000

Data Index: 143217 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.7849. Min Act: -0.0000

Data Index: 1034046 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.8474. Min Act: -0.0000

Data Index: 312366 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.3869. Min Act: -0.0000

Data Index: 148197 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.8164. Min Act: -0.0000

Data Index: 733463 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.4926. Min Act: -0.0000

Data Index: 1686138 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.4288. Min Act: -0.0000

Data Index: 1880639 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.2711. Min Act: -0.0000

Data Index: 1316593 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.2106. Min Act: -0.0000

Data Index: 1979345 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.3867. Min Act: -0.0000

Data Index: 1149934 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.2755. Min Act: -0.0000

Data Index: 1625796 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.0638. Min Act: -0.0000

Data Index: 631961 (The Pile)

Max Activating Token Index: 345

Text #19

Max Range: 4.8924. Min Range: -4.8924

Max Act: 3.1949. Min Act: -0.0000

Data Index: 1968636 (The Pile)

Max Activating Token Index: 16