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

Dataset: The Pile

Neuron 5020 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: 0.7462. Min Range: -0.7462

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1884928 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6358. Min Act: -0.0000

Data Index: 614991 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6070. Min Act: 0.0000

Data Index: 868116 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1577308 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6379. Min Act: -0.0000

Data Index: 855069 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6007. Min Act: -0.0000

Data Index: 487126 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1546180 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1943065 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5701. Min Act: -0.0000

Data Index: 478865 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5579. Min Act: -0.0000

Data Index: 33976 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1777053 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5645. Min Act: -0.0000

Data Index: 282310 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5242. Min Act: -0.0000

Data Index: 700314 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5557. Min Act: -0.0000

Data Index: 887012 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5102. Min Act: -0.0000

Data Index: 754292 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1383078 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.4992. Min Act: -0.0000

Data Index: 64614 (The Pile)

Max Activating Token Index: 898

Text #17

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1405834 (The Pile)

Max Activating Token Index: 584

Text #18

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1874830 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.4856. Min Act: -0.0000

Data Index: 75696 (The Pile)

Max Activating Token Index: 31