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

Dataset: The Pile

Neuron 3580 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0000

Data Index: 249267 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1763295 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0833. Min Act: -0.0000

Data Index: 917566 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1577265 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0821. Min Act: -0.0000

Data Index: 221443 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0819. Min Act: -0.0000

Data Index: 233691 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0818. Min Act: -0.0000

Data Index: 138559 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0813. Min Act: -0.0000

Data Index: 614133 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0809. Min Act: -0.0000

Data Index: 904030 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1731389 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0791. Min Act: -0.0000

Data Index: 1824932 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0773. Min Act: -0.0000

Data Index: 905666 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0769. Min Act: -0.0000

Data Index: 597856 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1783407 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1919030 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1931242 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1173033 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0754. Min Act: -0.0000

Data Index: 877144 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0746. Min Act: -0.0000

Data Index: 663179 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1143374 (The Pile)

Max Activating Token Index: 1023