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

Dataset: The Pile

Neuron 3172 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1657276 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8395. Min Act: -0.0000

Data Index: 377925 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1160582 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1394898 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7601. Min Act: -0.0000

Data Index: 985410 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6388. Min Act: -0.0000

Data Index: 220483 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6820. Min Act: -0.0000

Data Index: 41450 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6970. Min Act: -0.0000

Data Index: 276315 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1411182 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6642. Min Act: -0.0000

Data Index: 548697 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1000704 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1449711 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1202059 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1733017 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1643546 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1875470 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1581873 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1476197 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.4941. Min Act: 0.0002

Data Index: 381864 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1057632 (The Pile)

Max Activating Token Index: 713