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

Dataset: The Pile

Neuron 3175 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.2420. Min Act: -0.0000

Data Index: 292878 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5695. Min Act: -0.0000

Data Index: 131295 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4006. Min Act: -0.0000

Data Index: 766931 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.1840. Min Act: -0.0000

Data Index: 847878 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.1448. Min Act: -0.0000

Data Index: 1364384 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4137. Min Act: -0.0000

Data Index: 89928 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.3465. Min Act: -0.0000

Data Index: 141740 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.3680. Min Act: -0.0000

Data Index: 1439001 (The Pile)

Max Activating Token Index: 280

Text #8

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.1703. Min Act: -0.0000

Data Index: 110857 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.2997. Min Act: -0.0000

Data Index: 134155 (The Pile)

Max Activating Token Index: 755

Text #10

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4660. Min Act: -0.0000

Data Index: 1563729 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.0716. Min Act: -0.0000

Data Index: 145436 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.3920. Min Act: -0.0000

Data Index: 400606 (The Pile)

Max Activating Token Index: 197

Text #13

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.2016. Min Act: -0.0000

Data Index: 1987400 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.1625. Min Act: -0.0000

Data Index: 37328 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.1622. Min Act: -0.0000

Data Index: 1516711 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.1612. Min Act: -0.0000

Data Index: 345566 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.0249. Min Act: -0.0000

Data Index: 1271506 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.7234. Min Act: -0.0000

Data Index: 1735234 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.9265. Min Act: -0.0000

Data Index: 1036952 (The Pile)

Max Activating Token Index: 613