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

Dataset: The Pile

Neuron 362 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0739. Min Act: -0.0000

Data Index: 88832 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1462059 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0523. Min Act: -0.0000

Data Index: 582476 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9161. Min Act: -0.0000

Data Index: 38653 (The Pile)

Max Activating Token Index: 17

Text #4

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1222942 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1380840 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1713062 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9025. Min Act: -0.0000

Data Index: 253729 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8873. Min Act: -0.0000

Data Index: 628670 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9252. Min Act: -0.0000

Data Index: 645430 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8480. Min Act: -0.0000

Data Index: 225019 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1993108 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1363347 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1233791 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8218. Min Act: -0.0000

Data Index: 269105 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1120397 (The Pile)

Max Activating Token Index: 802

Text #16

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8392. Min Act: -0.0000

Data Index: 538646 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8012. Min Act: -0.0000

Data Index: 565262 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1092556 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1015822 (The Pile)

Max Activating Token Index: 813