Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3009 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.4363. Min Act: -0.0000

Data Index: 616804 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3736. Min Act: -0.0000

Data Index: 804215 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1247809 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1219787 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1596314 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1056910 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2873. Min Act: -0.0000

Data Index: 648410 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3251. Min Act: -0.0000

Data Index: 877094 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1736039 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1609416 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1474307 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1456865 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1818242 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1957880 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2693. Min Act: -0.0000

Data Index: 517748 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1174085 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2725. Min Act: -0.0000

Data Index: 984647 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1624523 (The Pile)

Max Activating Token Index: 264

Text #18

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1839885 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1714049 (The Pile)

Max Activating Token Index: 742