< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 34 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: 0.1480. Min Range: -0.1480

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1851837 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1596393 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1497764 (The Pile)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1278. Min Act: -0.0001

Data Index: 553074 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1844168 (The Pile)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1310592 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1213. Min Act: -0.0001

Data Index: 997872 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1817500 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1789210 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1127. Min Act: -0.0001

Data Index: 297042 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0990. Min Act: -0.0001

Data Index: 828582 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1821283 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1152. Min Act: -0.0001

Data Index: 431269 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1874280 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1151. Min Act: -0.0001

Data Index: 413056 (The Pile)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1832771 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1384813 (The Pile)

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1021. Min Act: -0.0001

Data Index: 464358 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1381627 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1063. Min Act: -0.0001

Data Index: 824763 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #19