Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4000 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0940. Min Range: -1.0940

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1002929 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 1.0940. Min Range: -1.0940

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1952918 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1031958 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.9314. Min Act: -0.0000

Data Index: 954401 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1655914 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8590. Min Act: -0.0000

Data Index: 140980 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7767. Min Act: -0.0000

Data Index: 798984 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7986. Min Act: -0.0000

Data Index: 751543 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7796. Min Act: -0.0000

Data Index: 135509 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7804. Min Act: -0.0000

Data Index: 263720 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1502031 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1260352 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1855315 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1714109 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7047. Min Act: -0.0000

Data Index: 525754 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7454. Min Act: -0.0000

Data Index: 385858 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1153019 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1463570 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7572. Min Act: -0.0000

Data Index: 416241 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1839902 (The Pile)

Max Activating Token Index: 882