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

Dataset: The Pile

Neuron 646 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1066118 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1582474 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1530888 (The Pile)

Max Activating Token Index: 740

Text #3

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1567713 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4031. Min Act: -0.0000

Data Index: 101227 (The Pile)

Max Activating Token Index: 1000

Text #5

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3812. Min Act: -0.0000

Data Index: 353818 (The Pile)

Max Activating Token Index: 559

Text #6

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1157881 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4193. Min Act: -0.0000

Data Index: 615190 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1423901 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3631. Min Act: -0.0000

Data Index: 172278 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4077. Min Act: -0.0000

Data Index: 178997 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3843. Min Act: -0.0000

Data Index: 800533 (The Pile)

Max Activating Token Index: 1005

Text #12

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1952484 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1478180 (The Pile)

Max Activating Token Index: 1001

Text #14

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3589. Min Act: -0.0000

Data Index: 424612 (The Pile)

Max Activating Token Index: 802

Text #15

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3410. Min Act: -0.0000

Data Index: 208638 (The Pile)

Max Activating Token Index: 785

Text #16

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3124. Min Act: -0.0000

Data Index: 954839 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3521. Min Act: -0.0000

Data Index: 605349 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3512. Min Act: -0.0000

Data Index: 12018 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1218092 (The Pile)

Max Activating Token Index: 898