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

Dataset: The Pile

Neuron 3749 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: 0.4200. Min Range: -0.4200

Max Act: 0.4200. Min Act: -0.0000

Data Index: 290086 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1475895 (The Pile)

Max Activating Token Index: 657

Text #2

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1377455 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3243. Min Act: -0.0000

Data Index: 428468 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1473395 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1197141 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3026. Min Act: -0.0000

Data Index: 116734 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2890. Min Act: -0.0000

Data Index: 105174 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3587. Min Act: -0.0000

Data Index: 409774 (The Pile)

Max Activating Token Index: 982

Text #9

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1773776 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2883. Min Act: -0.0000

Data Index: 467149 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1041615 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1865460 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2812. Min Act: -0.0000

Data Index: 278578 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3103. Min Act: -0.0000

Data Index: 43710 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1632784 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2878. Min Act: -0.0000

Data Index: 992306 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1741874 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1917414 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2592. Min Act: -0.0000

Data Index: 120645 (The Pile)

Max Activating Token Index: 518