< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5099 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: 0.9346. Min Range: -0.9346

Max Act: 0.9346. Min Act: -0.0000

Data Index: 561268 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1794777 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1392337 (The Pile)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1914426 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1433850 (The Pile)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1115792 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7784. Min Act: -0.0000

Data Index: 279104 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.8186. Min Act: -0.0000

Data Index: 138220 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7545. Min Act: -0.0000

Data Index: 198863 (The Pile)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7291. Min Act: -0.0000

Data Index: 706588 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7624. Min Act: -0.0000

Data Index: 105522 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1399479 (The Pile)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7260. Min Act: -0.0000

Data Index: 301160 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1744192 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1117456 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1175890 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.6833. Min Act: -0.0000

Data Index: 801258 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1485489 (The Pile)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1177367 (The Pile)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9346. Min Range: -0.9346

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1171370 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #19