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

Dataset: The Pile

Neuron 2139 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: 1.3290. Min Range: -1.3290

Max Act: 1.3290. Min Act: -0.0000

Data Index: 1605341 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2571. Min Act: -0.0000

Data Index: 1051501 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1664038 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1993911 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.0381. Min Act: -0.0000

Data Index: 406650 (The Pile)

Max Activating Token Index: 649

Text #5

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.0274. Min Act: -0.0000

Data Index: 494714 (The Pile)

Max Activating Token Index: 440

Text #6

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1562651 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9972. Min Act: -0.0000

Data Index: 546111 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.7181. Min Act: -0.0000

Data Index: 653168 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8973. Min Act: -0.0000

Data Index: 285259 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8918. Min Act: -0.0000

Data Index: 855762 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1029539 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8563. Min Act: -0.0000

Data Index: 419720 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1781107 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1424945 (The Pile)

Max Activating Token Index: 828

Text #15

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9615. Min Act: -0.0000

Data Index: 419788 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1090097 (The Pile)

Max Activating Token Index: 472

Text #17

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1777093 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8406. Min Act: -0.0000

Data Index: 657874 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8238. Min Act: -0.0000

Data Index: 54266 (The Pile)

Max Activating Token Index: 753