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

Dataset: The Pile

Neuron 3049 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: 1.7123. Min Range: -1.7123

Max Act: 1.7123. Min Act: -0.0000

Data Index: 634743 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.6702. Min Act: -0.0000

Data Index: 1509114 (The Pile)

Max Activating Token Index: 507

Text #2

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5605. Min Act: -0.0000

Data Index: 1170321 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.6429. Min Act: -0.0000

Data Index: 630460 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5943. Min Act: -0.0000

Data Index: 1965036 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1225402 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5586. Min Act: -0.0000

Data Index: 364319 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5087. Min Act: -0.0000

Data Index: 407598 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4620. Min Act: -0.0000

Data Index: 1315779 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1013825 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5153. Min Act: -0.0000

Data Index: 46075 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3471. Min Act: -0.0000

Data Index: 685704 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3378. Min Act: -0.0000

Data Index: 1697099 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3880. Min Act: -0.0000

Data Index: 356885 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4084. Min Act: -0.0000

Data Index: 102771 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1534753 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3972. Min Act: -0.0000

Data Index: 699482 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3748. Min Act: -0.0000

Data Index: 807442 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4458. Min Act: -0.0000

Data Index: 696884 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3746. Min Act: -0.0000

Data Index: 703190 (The Pile)

Max Activating Token Index: 351