< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4088 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.9622. Min Act: -0.0001

Data Index: 1507360 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6832. Min Act: -0.0001

Data Index: 1512144 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6784. Min Act: -0.0001

Data Index: 1067281 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6878. Min Act: -0.0001

Data Index: 1706330 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6629. Min Act: -0.0001

Data Index: 851493 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6369. Min Act: -0.0001

Data Index: 239392 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6505. Min Act: -0.0001

Data Index: 1258270 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6742. Min Act: -0.0001

Data Index: 590312 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6349. Min Act: -0.0001

Data Index: 867388 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6528. Min Act: -0.0001

Data Index: 1681115 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6722. Min Act: -0.0001

Data Index: 985273 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6311. Min Act: -0.0001

Data Index: 1119318 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6726. Min Act: -0.0001

Data Index: 513346 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6717. Min Act: -0.0001

Data Index: 1896631 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6698. Min Act: -0.0001

Data Index: 1443274 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6481. Min Act: -0.0001

Data Index: 246822 (The Pile)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6903. Min Act: -0.0001

Data Index: 1481304 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6411. Min Act: -0.0001

Data Index: 1852708 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6791. Min Act: -0.0001

Data Index: 527027 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6168. Min Act: -0.0001

Data Index: 1416336 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #19