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

Dataset: The Pile

Neuron 1791 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: 3.6710. Min Range: -3.6710

Max Act: 3.6710. Min Act: -0.0000

Data Index: 1970747 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 3.6710. Min Range: -3.6710

Max Act: 3.0403. Min Act: -0.0000

Data Index: 1415900 (The Pile)

Max Activating Token Index: 426

Text #2

Max Range: 3.6710. Min Range: -3.6710

Max Act: 3.3311. Min Act: -0.0000

Data Index: 788341 (The Pile)

Max Activating Token Index: 752

Text #3

Max Range: 3.6710. Min Range: -3.6710

Max Act: 3.3801. Min Act: -0.0000

Data Index: 764233 (The Pile)

Max Activating Token Index: 798

Text #4

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.9177. Min Act: -0.0000

Data Index: 965902 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 3.6710. Min Range: -3.6710

Max Act: 3.0982. Min Act: -0.0000

Data Index: 544397 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.7031. Min Act: -0.0000

Data Index: 1355968 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.7639. Min Act: -0.0000

Data Index: 1347783 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.9050. Min Act: -0.0000

Data Index: 360062 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.2092. Min Act: -0.0000

Data Index: 607613 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.6475. Min Act: -0.0000

Data Index: 716487 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.5230. Min Act: -0.0000

Data Index: 355595 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.8300. Min Act: -0.0000

Data Index: 1676706 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.5903. Min Act: -0.0000

Data Index: 1022726 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.2415. Min Act: -0.0000

Data Index: 1415679 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.3934. Min Act: -0.0000

Data Index: 1538606 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.4993. Min Act: -0.0000

Data Index: 144620 (The Pile)

Max Activating Token Index: 414

Text #17

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.4979. Min Act: -0.0000

Data Index: 1534608 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.5417. Min Act: -0.0000

Data Index: 1605428 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 3.6710. Min Range: -3.6710

Max Act: 2.6498. Min Act: -0.0000

Data Index: 908429 (The Pile)

Max Activating Token Index: 791