< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 33 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7827. Min Act: -0.0000

Data Index: 564167 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1531110 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7664. Min Act: -0.0000

Data Index: 356031 (The Pile)

Max Activating Token Index: 966

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1900360 (The Pile)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7410. Min Act: -0.0000

Data Index: 258879 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7285. Min Act: -0.0000

Data Index: 987576 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7006. Min Act: -0.0000

Data Index: 181051 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6356. Min Act: -0.0000

Data Index: 847897 (The Pile)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7127. Min Act: -0.0000

Data Index: 993606 (The Pile)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6884. Min Act: -0.0000

Data Index: 500968 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6643. Min Act: -0.0000

Data Index: 76147 (The Pile)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6767. Min Act: -0.0000

Data Index: 877177 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1026609 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1119693 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1483667 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1325480 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1797660 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6674. Min Act: -0.0000

Data Index: 494006 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6841. Min Act: -0.0000

Data Index: 853829 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6594. Min Act: -0.0000

Data Index: 917328 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #19