< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3029 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: 1.6005. Min Range: -1.6005

Max Act: 1.6005. Min Act: -0.0001

Data Index: 1213555 (The Pile)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.5494. Min Act: -0.0001

Data Index: 841364 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.4734. Min Act: -0.0000

Data Index: 1406110 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2181. Min Act: -0.0000

Data Index: 84606 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.3197. Min Act: -0.0001

Data Index: 1023981 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1719776 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1908. Min Act: -0.0001

Data Index: 430017 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1106588 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2545. Min Act: -0.0001

Data Index: 309657 (The Pile)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2404. Min Act: -0.0001

Data Index: 1832295 (The Pile)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.3076. Min Act: -0.0001

Data Index: 365437 (The Pile)

Max Activating Token Index: 1008

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2181. Min Act: -0.0001

Data Index: 1323584 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2579. Min Act: -0.0001

Data Index: 1236837 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1734. Min Act: -0.0001

Data Index: 205323 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1968. Min Act: -0.0001

Data Index: 262430 (The Pile)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1631. Min Act: -0.0001

Data Index: 1788600 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1641. Min Act: -0.0001

Data Index: 1876242 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1531. Min Act: -0.0000

Data Index: 1560712 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1903. Min Act: -0.0001

Data Index: 1822374 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1186. Min Act: -0.0001

Data Index: 1659703 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #19