< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 14 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4675. Min Act: -0.0000

Data Index: 427478 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4148. Min Act: -0.0001

Data Index: 502434 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4219. Min Act: -0.0001

Data Index: 1613268 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1745265 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4318. Min Act: -0.0001

Data Index: 205770 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1287939 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4050. Min Act: -0.0000

Data Index: 581405 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3896. Min Act: -0.0001

Data Index: 875554 (The Pile)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3905. Min Act: 0.0000

Data Index: 218065 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1815161 (The Pile)

Max Activating Token Index: 226

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3906. Min Act: -0.0001

Data Index: 970102 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3701. Min Act: -0.0001

Data Index: 921080 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3403. Min Act: -0.0001

Data Index: 961589 (The Pile)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1319451 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1303878 (The Pile)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.2972. Min Act: -0.0001

Data Index: 634701 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3598. Min Act: -0.0000

Data Index: 454144 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3717. Min Act: -0.0000

Data Index: 725690 (The Pile)

Max Activating Token Index: 713

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1939567 (The Pile)

Max Activating Token Index: 968

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3569. Min Act: -0.0001

Data Index: 1751781 (The Pile)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #19