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

Dataset: The Pile

Neuron 3379 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2759. Min Range: -7.2759

Max Act: 7.2311. Min Act: -0.0000

Data Index: 1162180 (The Pile)

Max Activating Token Index: 383

Text #1

Max Range: 7.2759. Min Range: -7.2759

Max Act: 7.2759. Min Act: 0.0000

Data Index: 110797 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 7.2759. Min Range: -7.2759

Max Act: 7.1118. Min Act: -0.0000

Data Index: 1555097 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 7.2759. Min Range: -7.2759

Max Act: 7.1221. Min Act: -0.0000

Data Index: 1518765 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.7920. Min Act: -0.0000

Data Index: 258799 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.5649. Min Act: 0.0000

Data Index: 371749 (The Pile)

Max Activating Token Index: 221

Text #6

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.0782. Min Act: -0.0000

Data Index: 913513 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.5576. Min Act: -0.0000

Data Index: 498033 (The Pile)

Max Activating Token Index: 869

Text #8

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.1790. Min Act: 0.0000

Data Index: 476757 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.3448. Min Act: -0.0000

Data Index: 1966815 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.3315. Min Act: -0.0000

Data Index: 1071528 (The Pile)

Max Activating Token Index: 565

Text #11

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.2312. Min Act: -0.0000

Data Index: 451965 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.7718. Min Act: -0.0000

Data Index: 1320069 (The Pile)

Max Activating Token Index: 894

Text #13

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.1895. Min Act: -0.0000

Data Index: 1448607 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.3162. Min Act: -0.0000

Data Index: 52892 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 7.2759. Min Range: -7.2759

Max Act: 7.0466. Min Act: -0.0000

Data Index: 818181 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.2291. Min Act: -0.0000

Data Index: 1834758 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.3759. Min Act: -0.0000

Data Index: 140495 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 7.2759. Min Range: -7.2759

Max Act: 5.5583. Min Act: -0.0000

Data Index: 691118 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 7.2759. Min Range: -7.2759

Max Act: 6.0597. Min Act: -0.0000

Data Index: 1534613 (The Pile)

Max Activating Token Index: 899