< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3038 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.4327. Min Act: -0.0001

Data Index: 1325193 (The Pile)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.2684. Min Act: -0.0001

Data Index: 1193903 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.1652. Min Act: -0.0001

Data Index: 1892090 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.1696. Min Act: -0.0001

Data Index: 106943 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.1411. Min Act: -0.0001

Data Index: 151410 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.1803. Min Act: -0.0001

Data Index: 1715910 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.0979. Min Act: -0.0001

Data Index: 1787201 (The Pile)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4327. Min Range: -1.4327

Max Act: 0.9139. Min Act: -0.0001

Data Index: 189894 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4327. Min Range: -1.4327

Max Act: 0.9771. Min Act: -0.0001

Data Index: 816443 (The Pile)

Max Activating Token Index: 769

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.0878. Min Act: -0.0001

Data Index: 1569869 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.1340. Min Act: -0.0001

Data Index: 252725 (The Pile)

Max Activating Token Index: 90

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.0989. Min Act: -0.0001

Data Index: 297887 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.1160. Min Act: -0.0001

Data Index: 1013533 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.0732. Min Act: -0.0001

Data Index: 72520 (The Pile)

Max Activating Token Index: 290

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.0638. Min Act: -0.0001

Data Index: 375618 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.0733. Min Act: -0.0001

Data Index: 1626870 (The Pile)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.1595. Min Act: -0.0001

Data Index: 1818105 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.0252. Min Act: -0.0001

Data Index: 1149971 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.0649. Min Act: -0.0001

Data Index: 66024 (The Pile)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4327. Min Range: -1.4327

Max Act: 1.0399. Min Act: -0.0001

Data Index: 1182245 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #19