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

Dataset: The Pile

Neuron 1934 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3600. Min Act: -0.0000

Data Index: 174076 (The Pile)

Max Activating Token Index: 14

Text #1

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3603. Min Act: -0.0000

Data Index: 516816 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1295451 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1696074 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3232. Min Act: -0.0000

Data Index: 97925 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1626090 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2933. Min Act: -0.0000

Data Index: 942572 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2867. Min Act: -0.0000

Data Index: 485184 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1000534 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1797783 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2913. Min Act: -0.0000

Data Index: 765259 (The Pile)

Max Activating Token Index: 730

Text #11

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3304. Min Act: -0.0000

Data Index: 561671 (The Pile)

Max Activating Token Index: 782

Text #12

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1535178 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1289420 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2698. Min Act: -0.0000

Data Index: 403215 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2915. Min Act: -0.0000

Data Index: 54912 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2752. Min Act: -0.0000

Data Index: 957236 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2733. Min Act: -0.0000

Data Index: 504940 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1260759 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1661416 (The Pile)

Max Activating Token Index: 763