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

Dataset: The Pile

Neuron 5102 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1426562 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.5979. Min Act: -0.0000

Data Index: 244670 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.5710. Min Act: -0.0000

Data Index: 955530 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1864242 (The Pile)

Max Activating Token Index: 635

Text #4

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.5548. Min Act: -0.0000

Data Index: 106740 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1432487 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1893660 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3819. Min Act: 0.0000

Data Index: 363713 (The Pile)

Max Activating Token Index: 841

Text #8

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1813127 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1017688 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1792357 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1257171 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1019784 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1103485 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1344663 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3334. Min Act: -0.0000

Data Index: 874867 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1555630 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3311. Min Act: -0.0000

Data Index: 606828 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3309. Min Act: -0.0000

Data Index: 779467 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.6716. Min Range: -0.6716

Max Act: 0.3507. Min Act: -0.0000

Data Index: 95467 (The Pile)

Max Activating Token Index: 239