< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 48 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1781. Min Act: -0.0002

Data Index: 214528 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1755. Min Act: -0.0001

Data Index: 756647 (The Pile)

Max Activating Token Index: 981

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1404. Min Act: -0.0002

Data Index: 475092 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1382. Min Act: -0.0002

Data Index: 110732 (The Pile)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1521505 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1756841 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1302. Min Act: -0.0002

Data Index: 646450 (The Pile)

Max Activating Token Index: 90

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1924799 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1883188 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1193. Min Act: -0.0002

Data Index: 610258 (The Pile)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1266. Min Act: -0.0002

Data Index: 1850459 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1223. Min Act: -0.0002

Data Index: 932056 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1222. Min Act: -0.0002

Data Index: 85617 (The Pile)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1025271 (The Pile)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1262411 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1230. Min Act: -0.0002

Data Index: 325681 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1720851 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1323. Min Act: -0.0002

Data Index: 1829116 (The Pile)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1131. Min Act: -0.0001

Data Index: 704250 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1741842 (The Pile)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #19