< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3043 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.6638. Min Act: -0.0001

Data Index: 574688 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5986. Min Act: -0.0001

Data Index: 1675454 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.6801. Min Act: -0.0001

Data Index: 1369044 (The Pile)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.6082. Min Act: -0.0001

Data Index: 1830469 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1249932 (The Pile)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.6412. Min Act: -0.0001

Data Index: 151960 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.6137. Min Act: -0.0001

Data Index: 1599900 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5873. Min Act: -0.0001

Data Index: 1631750 (The Pile)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5747. Min Act: -0.0001

Data Index: 1668551 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.6004. Min Act: -0.0001

Data Index: 1637213 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5798. Min Act: -0.0000

Data Index: 185205 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5887. Min Act: -0.0001

Data Index: 797198 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5514. Min Act: -0.0001

Data Index: 1996644 (The Pile)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5827. Min Act: -0.0001

Data Index: 317853 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5512. Min Act: -0.0001

Data Index: 1740500 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5309. Min Act: -0.0001

Data Index: 1241215 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5463. Min Act: -0.0001

Data Index: 278474 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5201. Min Act: -0.0001

Data Index: 980925 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5368. Min Act: -0.0001

Data Index: 1603559 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6801. Min Range: -0.6801

Max Act: 0.5542. Min Act: -0.0001

Data Index: 515139 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #19