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

Dataset: The Pile

Neuron 4791 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: 1.5919. Min Range: -1.5919

Max Act: 1.5919. Min Act: -0.0000

Data Index: 496730 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.4404. Min Act: -0.0000

Data Index: 1788300 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.4343. Min Act: -0.0000

Data Index: 304580 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1822626 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3184. Min Act: -0.0000

Data Index: 936133 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2156. Min Act: -0.0000

Data Index: 1049787 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1490069 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2285. Min Act: -0.0000

Data Index: 410588 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2086. Min Act: -0.0000

Data Index: 965731 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1510. Min Act: -0.0000

Data Index: 420320 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1166907 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0890. Min Act: -0.0000

Data Index: 879139 (The Pile)

Max Activating Token Index: 526

Text #12

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1722631 (The Pile)

Max Activating Token Index: 807

Text #13

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0732. Min Act: -0.0000

Data Index: 1024865 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1576938 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0908. Min Act: -0.0000

Data Index: 197768 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.9515. Min Act: -0.0000

Data Index: 938596 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0604. Min Act: -0.0000

Data Index: 400878 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.9947. Min Act: -0.0000

Data Index: 226460 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1882147 (The Pile)

Max Activating Token Index: 935