< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 49 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1535. Min Act: -0.0002

Data Index: 149992 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1507. Min Act: -0.0002

Data Index: 1406188 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1741. Min Act: -0.0002

Data Index: 1830453 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1511164 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1457. Min Act: -0.0002

Data Index: 842980 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1326. Min Act: -0.0002

Data Index: 243556 (The Pile)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1335. Min Act: -0.0002

Data Index: 267047 (The Pile)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1302. Min Act: -0.0002

Data Index: 1239036 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1295. Min Act: -0.0002

Data Index: 188945 (The Pile)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1302. Min Act: -0.0002

Data Index: 681875 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1336. Min Act: -0.0002

Data Index: 710474 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1222. Min Act: -0.0002

Data Index: 729332 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1309. Min Act: -0.0002

Data Index: 1104930 (The Pile)

Max Activating Token Index: 726

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1376. Min Act: -0.0002

Data Index: 1068771 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1319. Min Act: -0.0002

Data Index: 1830994 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1704750 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1506489 (The Pile)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1303. Min Act: -0.0002

Data Index: 577507 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1222. Min Act: -0.0002

Data Index: 785011 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1198. Min Act: -0.0002

Data Index: 102614 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #19