< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 15 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: 0.2564. Min Range: -0.2564

Max Act: 0.2176. Min Act: -0.0001

Data Index: 1814012 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2484. Min Act: -0.0001

Data Index: 198944 (The Pile)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2564. Min Act: -0.0001

Data Index: 271190 (The Pile)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2313. Min Act: -0.0001

Data Index: 1969792 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1545217 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1120220 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2085. Min Act: -0.0001

Data Index: 1300221 (The Pile)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2068. Min Act: -0.0001

Data Index: 1347186 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1186634 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1025835 (The Pile)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1441961 (The Pile)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2136. Min Act: -0.0001

Data Index: 302888 (The Pile)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2058. Min Act: -0.0001

Data Index: 1862650 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2038. Min Act: -0.0001

Data Index: 1330164 (The Pile)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.1845. Min Act: -0.0001

Data Index: 1002797 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.1860. Min Act: -0.0001

Data Index: 135946 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.1914. Min Act: -0.0001

Data Index: 888191 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.1792. Min Act: -0.0001

Data Index: 512015 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.2056. Min Act: -0.0001

Data Index: 323560 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2564. Min Range: -0.2564

Max Act: 0.1928. Min Act: -0.0001

Data Index: 1003614 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #19