< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 62 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: 0.5973. Min Range: -0.5973

Max Act: 0.5973. Min Act: -0.0001

Data Index: 1061913 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5761. Min Act: -0.0001

Data Index: 785112 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5710. Min Act: -0.0001

Data Index: 1310848 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5612. Min Act: -0.0001

Data Index: 957136 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5146. Min Act: -0.0001

Data Index: 160056 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5344. Min Act: -0.0001

Data Index: 560924 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5117. Min Act: -0.0001

Data Index: 850603 (The Pile)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1923925 (The Pile)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4949. Min Act: -0.0001

Data Index: 689794 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4896. Min Act: -0.0001

Data Index: 482233 (The Pile)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1234889 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5271. Min Act: -0.0001

Data Index: 254414 (The Pile)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5129. Min Act: -0.0001

Data Index: 1106585 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4873. Min Act: -0.0001

Data Index: 827864 (The Pile)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5034. Min Act: -0.0001

Data Index: 1729547 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4945. Min Act: -0.0001

Data Index: 1099380 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5053. Min Act: -0.0001

Data Index: 1709000 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4688. Min Act: -0.0001

Data Index: 1389801 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4675. Min Act: -0.0001

Data Index: 466936 (The Pile)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4775. Min Act: -0.0001

Data Index: 565555 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #19