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

Dataset: The Pile

Neuron 3226 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5102. Min Range: -4.5102

Max Act: 4.5102. Min Act: -0.0000

Data Index: 608760 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 4.5102. Min Range: -4.5102

Max Act: 4.3364. Min Act: -0.0000

Data Index: 1694957 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.7424. Min Act: -0.0000

Data Index: 627740 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.5837. Min Act: -0.0000

Data Index: 1466814 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.5842. Min Act: -0.0000

Data Index: 1086012 (The Pile)

Max Activating Token Index: 713

Text #5

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.5193. Min Act: -0.0000

Data Index: 1594588 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.5971. Min Act: -0.0000

Data Index: 225960 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.3815. Min Act: -0.0000

Data Index: 1435928 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.9726. Min Act: -0.0000

Data Index: 857950 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.9892. Min Act: -0.0000

Data Index: 915514 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.8834. Min Act: -0.0000

Data Index: 1543481 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.2252. Min Act: -0.0000

Data Index: 1732061 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.1393. Min Act: -0.0000

Data Index: 1850154 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.8632. Min Act: -0.0000

Data Index: 1066462 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.9456. Min Act: -0.0000

Data Index: 1199132 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.6610. Min Act: -0.0000

Data Index: 438732 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.0044. Min Act: -0.0000

Data Index: 474851 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.6949. Min Act: -0.0000

Data Index: 658759 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.8979. Min Act: -0.0000

Data Index: 1126910 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.6067. Min Act: -0.0000

Data Index: 289130 (The Pile)

Max Activating Token Index: 550