< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 21 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: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1090999 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9806. Min Act: -0.0001

Data Index: 1720782 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9734. Min Act: -0.0001

Data Index: 381399 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9607. Min Act: -0.0001

Data Index: 1897318 (The Pile)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9817. Min Act: -0.0001

Data Index: 75938 (The Pile)

Max Activating Token Index: 422

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9765. Min Act: -0.0001

Data Index: 1701402 (The Pile)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9733. Min Act: -0.0001

Data Index: 1286251 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9606. Min Act: -0.0001

Data Index: 1530186 (The Pile)

Max Activating Token Index: 226

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9835. Min Act: -0.0001

Data Index: 1813649 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9561. Min Act: -0.0001

Data Index: 1182947 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9389. Min Act: -0.0001

Data Index: 470141 (The Pile)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9307. Min Act: -0.0001

Data Index: 504007 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9340. Min Act: -0.0001

Data Index: 455297 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9319. Min Act: -0.0001

Data Index: 574717 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9620. Min Act: -0.0001

Data Index: 1089302 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9221. Min Act: -0.0001

Data Index: 1836724 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9125. Min Act: -0.0001

Data Index: 1702608 (The Pile)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9094. Min Act: -0.0001

Data Index: 693842 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8832. Min Act: -0.0001

Data Index: 1301360 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8711. Min Act: -0.0001

Data Index: 555317 (The Pile)

Max Activating Token Index: 97

Click toggle to see full text

Truncated

Full Text #19