< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5093 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: 1.5448. Min Range: -1.5448

Max Act: 1.5448. Min Act: -0.0000

Data Index: 95740 (The Pile)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.2500. Min Act: -0.0000

Data Index: 1468840 (The Pile)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.3059. Min Act: 0.0000

Data Index: 1991769 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1345311 (The Pile)

Max Activating Token Index: 371

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.2792. Min Act: -0.0000

Data Index: 953303 (The Pile)

Max Activating Token Index: 769

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1778. Min Act: -0.0000

Data Index: 919393 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.2331. Min Act: -0.0000

Data Index: 604703 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1478. Min Act: -0.0000

Data Index: 895834 (The Pile)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.2076. Min Act: -0.0000

Data Index: 265445 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1320. Min Act: -0.0000

Data Index: 966103 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1800. Min Act: -0.0000

Data Index: 533328 (The Pile)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1906845 (The Pile)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1809. Min Act: -0.0000

Data Index: 1864736 (The Pile)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1715060 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1097. Min Act: -0.0000

Data Index: 738271 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1831. Min Act: -0.0000

Data Index: 891819 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1358002 (The Pile)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.2487. Min Act: -0.0000

Data Index: 318561 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.1411. Min Act: 0.0001

Data Index: 443420 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5448. Min Range: -1.5448

Max Act: 1.2160. Min Act: -0.0000

Data Index: 179240 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #19