< Prev | Home | Model | Random | Next >

Model: SoLU Model: 2 Layers, 2944 Neurons per Layer

Dataset: The Pile

Neuron 33 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')



Text #0

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1559. Min Act: -0.0002

Data Index: 464595 (The Pile)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1455. Min Act: -0.0002

Data Index: 1742757 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1364. Min Act: -0.0002

Data Index: 1446671 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1309. Min Act: -0.0002

Data Index: 1310725 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1893813 (The Pile)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1238. Min Act: -0.0002

Data Index: 465252 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1190. Min Act: -0.0002

Data Index: 663444 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1223. Min Act: -0.0002

Data Index: 663421 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1877601 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1012445 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1196. Min Act: -0.0002

Data Index: 1472531 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1231. Min Act: -0.0002

Data Index: 996226 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1202. Min Act: -0.0002

Data Index: 1364307 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1199. Min Act: -0.0002

Data Index: 377062 (The Pile)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1184. Min Act: -0.0002

Data Index: 1199893 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1186. Min Act: -0.0002

Data Index: 1723553 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1785099 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1196. Min Act: -0.0002

Data Index: 1013932 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1826520 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1184. Min Act: -0.0002

Data Index: 1835177 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #19