< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5093 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.3326. Min Range: -2.3326

Max Act: 2.3326. Min Act: -0.0000

Data Index: 481701 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.8772. Min Act: 0.0000

Data Index: 1712375 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.7070. Min Act: -0.0000

Data Index: 447007 (The Pile)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.5015. Min Act: -0.0000

Data Index: 1341015 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.4010. Min Act: -0.0000

Data Index: 920132 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1387059 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.3167. Min Act: -0.0000

Data Index: 1244696 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.2174. Min Act: 0.0000

Data Index: 1761695 (The Pile)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1571567 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1871759 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.2089. Min Act: -0.0000

Data Index: 1364820 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1815554 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1515110 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1880339 (The Pile)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1545356 (The Pile)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1983146 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.0866. Min Act: 0.0001

Data Index: 1977716 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1166305 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.1223. Min Act: -0.0000

Data Index: 172877 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3326. Min Range: -2.3326

Max Act: 1.1356. Min Act: -0.0000

Data Index: 109703 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #19