< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 16 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.5761. Min Act: -0.0000

Data Index: 187329 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.8147. Min Act: -0.0000

Data Index: 1942012 (The Pile)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.1988. Min Act: -0.0000

Data Index: 1461628 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.1777. Min Act: -0.0000

Data Index: 1466551 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.0132. Min Act: -0.0000

Data Index: 1595432 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.2441. Min Act: -0.0000

Data Index: 1236818 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.2297. Min Act: -0.0000

Data Index: 1451114 (The Pile)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.0390. Min Act: -0.0000

Data Index: 1476674 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8147. Min Range: -2.8147

Max Act: 1.8918. Min Act: -0.0000

Data Index: 797716 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.0946. Min Act: -0.0000

Data Index: 1373568 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.0541. Min Act: -0.0000

Data Index: 1059223 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.0632. Min Act: -0.0000

Data Index: 819591 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.0415. Min Act: -0.0000

Data Index: 239336 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8147. Min Range: -2.8147

Max Act: 1.7001. Min Act: -0.0000

Data Index: 629582 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8147. Min Range: -2.8147

Max Act: 1.9310. Min Act: -0.0000

Data Index: 84668 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8147. Min Range: -2.8147

Max Act: 1.9405. Min Act: -0.0000

Data Index: 584858 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8147. Min Range: -2.8147

Max Act: 1.9155. Min Act: -0.0000

Data Index: 1653231 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.0151. Min Act: -0.0000

Data Index: 814606 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.0283. Min Act: -0.0000

Data Index: 36520 (The Pile)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8147. Min Range: -2.8147

Max Act: 2.1347. Min Act: -0.0000

Data Index: 916531 (The Pile)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #19