< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 2021 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4912. Min Act: -0.0001

Data Index: 1544754 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4433. Min Act: -0.0001

Data Index: 561679 (The Pile)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4141. Min Act: -0.0001

Data Index: 715073 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4210. Min Act: -0.0001

Data Index: 798281 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4074. Min Act: -0.0001

Data Index: 472715 (The Pile)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4027. Min Act: -0.0001

Data Index: 318799 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3982. Min Act: -0.0001

Data Index: 1155661 (The Pile)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4249. Min Act: -0.0001

Data Index: 62241 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4056. Min Act: -0.0001

Data Index: 1770335 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3858. Min Act: -0.0001

Data Index: 327113 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3696. Min Act: -0.0001

Data Index: 689858 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3959. Min Act: -0.0001

Data Index: 849465 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3788. Min Act: -0.0001

Data Index: 132628 (The Pile)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3524. Min Act: -0.0001

Data Index: 1150245 (The Pile)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3645. Min Act: -0.0001

Data Index: 1806424 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3866. Min Act: -0.0001

Data Index: 1864345 (The Pile)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1643173 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3857. Min Act: -0.0001

Data Index: 70135 (The Pile)

Max Activating Token Index: 422

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3605. Min Act: -0.0001

Data Index: 382422 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3681. Min Act: -0.0001

Data Index: 227722 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #19