< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3018 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: 0.4851. Min Range: -0.4851

Max Act: 0.4851. Min Act: -0.0001

Data Index: 1369796 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4696. Min Act: -0.0000

Data Index: 983784 (The Pile)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1059863 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4462. Min Act: -0.0000

Data Index: 281527 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4276. Min Act: -0.0001

Data Index: 1498687 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1168314 (The Pile)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4002. Min Act: -0.0000

Data Index: 667559 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4551. Min Act: -0.0000

Data Index: 342668 (The Pile)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4088. Min Act: -0.0000

Data Index: 707314 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1290570 (The Pile)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1039392 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4267. Min Act: -0.0001

Data Index: 785458 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1282002 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1955288 (The Pile)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1936673 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3885. Min Act: -0.0001

Data Index: 1101042 (The Pile)

Max Activating Token Index: 705

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1292288 (The Pile)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3899. Min Act: -0.0000

Data Index: 277053 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3422. Min Act: -0.0000

Data Index: 582104 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1257102 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #19