< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 56 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.4675. Min Range: -6.4675

Max Act: 6.4675. Min Act: -0.0000

Data Index: 337841 (The Pile)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.4675. Min Range: -6.4675

Max Act: 5.6232. Min Act: -0.0000

Data Index: 663733 (The Pile)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.4675. Min Range: -6.4675

Max Act: 5.2312. Min Act: -0.0000

Data Index: 1581618 (The Pile)

Max Activating Token Index: 111

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.4675. Min Range: -6.4675

Max Act: 5.1735. Min Act: -0.0000

Data Index: 357679 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.4675. Min Range: -6.4675

Max Act: 5.1460. Min Act: 0.0000

Data Index: 1018038 (The Pile)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.9781. Min Act: -0.0000

Data Index: 1346761 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.4675. Min Range: -6.4675

Max Act: 5.0667. Min Act: 0.0000

Data Index: 987729 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.8459. Min Act: -0.0000

Data Index: 1764159 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.4973. Min Act: -0.0000

Data Index: 806364 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.9194. Min Act: -0.0000

Data Index: 1008922 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.9155. Min Act: 0.0000

Data Index: 449719 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.7474. Min Act: -0.0000

Data Index: 1562387 (The Pile)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.5738. Min Act: -0.0000

Data Index: 963053 (The Pile)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.2866. Min Act: -0.0000

Data Index: 1841111 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.3998. Min Act: -0.0000

Data Index: 295521 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.5264. Min Act: -0.0000

Data Index: 1526900 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.4588. Min Act: -0.0000

Data Index: 5821 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.3068. Min Act: 0.0000

Data Index: 1477705 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.1233. Min Act: -0.0000

Data Index: 1117056 (The Pile)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.4675. Min Range: -6.4675

Max Act: 4.1309. Min Act: -0.0000

Data Index: 1648422 (The Pile)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #19