< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 52 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.2007. Min Act: -0.0001

Data Index: 500871 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1763. Min Act: -0.0001

Data Index: 442247 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1575. Min Act: -0.0001

Data Index: 327096 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1599. Min Act: -0.0001

Data Index: 7643 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1764976 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1360. Min Act: -0.0001

Data Index: 136922 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1387. Min Act: -0.0001

Data Index: 282495 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1346859 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1370209 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1376. Min Act: -0.0001

Data Index: 847397 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1961006 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1903112 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1335. Min Act: -0.0001

Data Index: 468746 (The Pile)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1246. Min Act: -0.0001

Data Index: 949927 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1268159 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1391931 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1185. Min Act: -0.0001

Data Index: 185578 (The Pile)

Max Activating Token Index: 60

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1164. Min Act: -0.0001

Data Index: 964229 (The Pile)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1288. Min Act: -0.0001

Data Index: 630850 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1965904 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #19