< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 15 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 2.1580. Min Range: -2.1580

Max Act: 2.1580. Min Act: -0.0000

Data Index: 306703 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.9774. Min Act: 0.0000

Data Index: 379560 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.8547. Min Act: -0.0000

Data Index: 1545872 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.6397. Min Act: 0.0001

Data Index: 1732707 (The Pile)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.6515. Min Act: 0.0002

Data Index: 1966352 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.4687. Min Act: 0.0000

Data Index: 1250909 (The Pile)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.5137. Min Act: 0.0002

Data Index: 1789051 (The Pile)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.4002. Min Act: 0.0002

Data Index: 1461275 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.3230. Min Act: 0.0000

Data Index: 654136 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.3948. Min Act: 0.0002

Data Index: 1398056 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.2175. Min Act: -0.0000

Data Index: 411990 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.1861. Min Act: -0.0000

Data Index: 1502185 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.2139. Min Act: 0.0002

Data Index: 469841 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.2106. Min Act: -0.0000

Data Index: 997537 (The Pile)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1473634 (The Pile)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.1742. Min Act: -0.0000

Data Index: 843048 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.1482. Min Act: -0.0000

Data Index: 805385 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.1490. Min Act: -0.0000

Data Index: 829033 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.1693. Min Act: 0.0002

Data Index: 1539860 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.1947. Min Act: 0.0002

Data Index: 496178 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #19