< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 33 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2482. Min Act: -0.0001

Data Index: 703816 (The Pile)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2372. Min Act: -0.0001

Data Index: 984187 (The Pile)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2324. Min Act: -0.0001

Data Index: 803163 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2523. Min Act: -0.0001

Data Index: 1599316 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2322. Min Act: -0.0001

Data Index: 721624 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1986. Min Act: -0.0001

Data Index: 468841 (The Pile)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2259. Min Act: -0.0001

Data Index: 62666 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2261. Min Act: -0.0001

Data Index: 1257797 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2055. Min Act: -0.0001

Data Index: 894752 (The Pile)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2300. Min Act: -0.0001

Data Index: 404159 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2199. Min Act: -0.0001

Data Index: 1270981 (The Pile)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2145. Min Act: -0.0001

Data Index: 846796 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2237. Min Act: -0.0001

Data Index: 241350 (The Pile)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1570279 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2172. Min Act: -0.0001

Data Index: 1728263 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1361742 (The Pile)

Max Activating Token Index: 226

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2003. Min Act: -0.0001

Data Index: 57163 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2008. Min Act: -0.0001

Data Index: 254020 (The Pile)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1896. Min Act: -0.0001

Data Index: 983366 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1892139 (The Pile)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #19