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

Dataset: The Pile

Neuron 1238 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: 0.8792. Min Range: -0.8792

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1738543 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1464349 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7221. Min Act: -0.0000

Data Index: 136267 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7035. Min Act: -0.0000

Data Index: 122301 (The Pile)

Max Activating Token Index: 866

Text #4

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6838. Min Act: -0.0000

Data Index: 873939 (The Pile)

Max Activating Token Index: 714

Text #5

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6581. Min Act: -0.0000

Data Index: 840601 (The Pile)

Max Activating Token Index: 418

Text #6

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6741. Min Act: -0.0000

Data Index: 193309 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6727. Min Act: -0.0000

Data Index: 180163 (The Pile)

Max Activating Token Index: 880

Text #8

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1845745 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6664. Min Act: -0.0000

Data Index: 260247 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1579659 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1430686 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1364781 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1903047 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1562739 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6531. Min Act: -0.0000

Data Index: 895640 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1870876 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6379. Min Act: -0.0000

Data Index: 455211 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6636. Min Act: -0.0000

Data Index: 53244 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6529. Min Act: -0.0000

Data Index: 968617 (The Pile)

Max Activating Token Index: 1009