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

Dataset: The Pile

Neuron 93 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: 0.7791. Min Range: -0.7791

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1243078 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1549412 (The Pile)

Max Activating Token Index: 338

Text #2

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7622. Min Act: -0.0000

Data Index: 114677 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6126. Min Act: -0.0000

Data Index: 64526 (The Pile)

Max Activating Token Index: 541

Text #4

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1025492 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1500271 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5649. Min Act: -0.0000

Data Index: 852500 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1795159 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5587. Min Act: -0.0000

Data Index: 348698 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1723819 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5478. Min Act: -0.0000

Data Index: 257723 (The Pile)

Max Activating Token Index: 287

Text #11

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1262878 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5152. Min Act: -0.0000

Data Index: 301993 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.4685. Min Act: -0.0000

Data Index: 136894 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1029655 (The Pile)

Max Activating Token Index: 885

Text #15

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1754579 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1037142 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1603713 (The Pile)

Max Activating Token Index: 872

Text #18

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1124648 (The Pile)

Max Activating Token Index: 376

Text #19

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.4750. Min Act: -0.0000

Data Index: 838106 (The Pile)

Max Activating Token Index: 999