< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 54 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2273. Min Act: -0.0004

Data Index: 1498102 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2307. Min Act: -0.0004

Data Index: 565703 (The Pile)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2360. Min Act: -0.0004

Data Index: 1932647 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2275. Min Act: -0.0004

Data Index: 1345184 (The Pile)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2078. Min Act: -0.0004

Data Index: 1697534 (The Pile)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2156. Min Act: -0.0004

Data Index: 1373633 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2149. Min Act: -0.0004

Data Index: 1843592 (The Pile)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2053. Min Act: -0.0004

Data Index: 104230 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2194. Min Act: -0.0004

Data Index: 371953 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2170. Min Act: -0.0004

Data Index: 514684 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2015. Min Act: -0.0004

Data Index: 986094 (The Pile)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2120. Min Act: -0.0004

Data Index: 321019 (The Pile)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1894. Min Act: -0.0004

Data Index: 876891 (The Pile)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1935. Min Act: -0.0004

Data Index: 437550 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1986. Min Act: -0.0004

Data Index: 66102 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1893. Min Act: -0.0004

Data Index: 504237 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1949. Min Act: -0.0004

Data Index: 725699 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1949. Min Act: -0.0004

Data Index: 1932471 (The Pile)

Max Activating Token Index: 622

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2008. Min Act: -0.0004

Data Index: 1577878 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2007. Min Act: -0.0004

Data Index: 150125 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #19