< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 70 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.4636. Min Act: -0.0000

Data Index: 303729 (The Pile)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2856. Min Act: -0.0000

Data Index: 226391 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2345. Min Act: -0.0000

Data Index: 306577 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1057. Min Act: -0.0000

Data Index: 3090 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1501883 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1891. Min Act: -0.0000

Data Index: 1360961 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1048191 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1882433 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1071914 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1606. Min Act: -0.0000

Data Index: 377977 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2060. Min Act: -0.0000

Data Index: 1183058 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1253. Min Act: -0.0000

Data Index: 504783 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1336. Min Act: -0.0000

Data Index: 924614 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1967319 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1923922 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1001749 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1525699 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1257. Min Act: -0.0000

Data Index: 923457 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1021720 (The Pile)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1204528 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #19