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

Dataset: The Pile

Neuron 2039 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6201. Min Act: -0.0000

Data Index: 409221 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4763. Min Act: -0.0000

Data Index: 952069 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4300. Min Act: -0.0000

Data Index: 426937 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1624670 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1579746 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1649242 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4182. Min Act: -0.0000

Data Index: 375396 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4258. Min Act: -0.0000

Data Index: 240478 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4226. Min Act: -0.0000

Data Index: 758469 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4213. Min Act: -0.0000

Data Index: 576926 (The Pile)

Max Activating Token Index: 506

Text #10

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4046. Min Act: -0.0000

Data Index: 247402 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1002337 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1333545 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4050. Min Act: -0.0000

Data Index: 980863 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4057. Min Act: -0.0000

Data Index: 980047 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.3658. Min Act: -0.0000

Data Index: 840338 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.3849. Min Act: -0.0000

Data Index: 211051 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.3586. Min Act: -0.0000

Data Index: 520292 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.3436. Min Act: -0.0000

Data Index: 827453 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4127. Min Act: -0.0000

Data Index: 177020 (The Pile)

Max Activating Token Index: 977