< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 2012 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: 0.8157. Min Range: -0.8157

Max Act: 0.8157. Min Act: -0.0001

Data Index: 1996047 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6452. Min Act: -0.0001

Data Index: 211912 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6703. Min Act: -0.0001

Data Index: 1045157 (The Pile)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1868226 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6740. Min Act: -0.0001

Data Index: 1572196 (The Pile)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.7089. Min Act: -0.0001

Data Index: 1724807 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6665. Min Act: -0.0001

Data Index: 1696058 (The Pile)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5931. Min Act: -0.0001

Data Index: 801211 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1333588 (The Pile)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5817. Min Act: -0.0001

Data Index: 790731 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5868. Min Act: -0.0001

Data Index: 1940998 (The Pile)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5740. Min Act: -0.0001

Data Index: 1502384 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5818. Min Act: -0.0001

Data Index: 1021512 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1022944 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5461. Min Act: -0.0001

Data Index: 312459 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5095. Min Act: -0.0001

Data Index: 168422 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5258. Min Act: -0.0001

Data Index: 354753 (The Pile)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4983. Min Act: -0.0001

Data Index: 1976941 (The Pile)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5058. Min Act: -0.0001

Data Index: 944238 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5045. Min Act: -0.0001

Data Index: 1780235 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #19