< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 14 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.8415. Min Act: -0.0001

Data Index: 1657859 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6222. Min Act: -0.0001

Data Index: 190411 (The Pile)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7528. Min Act: -0.0001

Data Index: 714134 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7303. Min Act: -0.0001

Data Index: 470412 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7884. Min Act: -0.0001

Data Index: 726178 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.8019. Min Act: -0.0001

Data Index: 1238491 (The Pile)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7640. Min Act: -0.0001

Data Index: 1844367 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7313. Min Act: -0.0001

Data Index: 688053 (The Pile)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7256. Min Act: -0.0001

Data Index: 399561 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6880. Min Act: -0.0001

Data Index: 1373974 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6763. Min Act: -0.0001

Data Index: 755039 (The Pile)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7115. Min Act: -0.0001

Data Index: 1815375 (The Pile)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7082. Min Act: -0.0001

Data Index: 503954 (The Pile)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.5972. Min Act: -0.0001

Data Index: 518440 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6328. Min Act: -0.0001

Data Index: 1037642 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6928. Min Act: -0.0001

Data Index: 778187 (The Pile)

Max Activating Token Index: 945

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7003. Min Act: -0.0001

Data Index: 136814 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7928. Min Act: -0.0001

Data Index: 521685 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.5589. Min Act: -0.0001

Data Index: 433178 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7105. Min Act: -0.0001

Data Index: 929886 (The Pile)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #19