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

Dataset: The Pile

Neuron 4527 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: 1.2766. Min Range: -1.2766

Max Act: 1.2762. Min Act: 0.0001

Data Index: 829777 (The Pile)

Max Activating Token Index: 546

Text #1

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1673162 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1103. Min Act: -0.0000

Data Index: 493441 (The Pile)

Max Activating Token Index: 924

Text #3

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1583851 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1605. Min Act: -0.0000

Data Index: 103462 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1502. Min Act: -0.0000

Data Index: 1369606 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1642693 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0729. Min Act: -0.0000

Data Index: 217558 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0639. Min Act: -0.0000

Data Index: 242379 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0459. Min Act: -0.0000

Data Index: 1216093 (The Pile)

Max Activating Token Index: 532

Text #10

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1284. Min Act: -0.0000

Data Index: 1337362 (The Pile)

Max Activating Token Index: 411

Text #11

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1204. Min Act: -0.0000

Data Index: 695885 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1916. Min Act: -0.0000

Data Index: 1618759 (The Pile)

Max Activating Token Index: 764

Text #13

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1549. Min Act: -0.0000

Data Index: 414426 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1666163 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1026. Min Act: -0.0000

Data Index: 686457 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0982. Min Act: -0.0000

Data Index: 329536 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0781. Min Act: -0.0000

Data Index: 27540 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0749. Min Act: -0.0000

Data Index: 879608 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9596. Min Act: -0.0000

Data Index: 901227 (The Pile)

Max Activating Token Index: 577