< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3062 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.5240. Min Act: -0.0001

Data Index: 146029 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4009. Min Act: -0.0001

Data Index: 595931 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4100. Min Act: -0.0001

Data Index: 1579488 (The Pile)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3854. Min Act: -0.0001

Data Index: 205972 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4112. Min Act: -0.0001

Data Index: 1281999 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3761. Min Act: -0.0001

Data Index: 529256 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1116227 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1176405 (The Pile)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3608. Min Act: -0.0001

Data Index: 1987023 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3736. Min Act: -0.0001

Data Index: 688499 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3517. Min Act: -0.0001

Data Index: 917359 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3595. Min Act: -0.0001

Data Index: 716002 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3847. Min Act: -0.0001

Data Index: 211058 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3819. Min Act: -0.0001

Data Index: 1842717 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3721. Min Act: -0.0001

Data Index: 1758255 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3636. Min Act: -0.0001

Data Index: 127800 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3742. Min Act: -0.0001

Data Index: 1245094 (The Pile)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3613. Min Act: -0.0001

Data Index: 999035 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3479. Min Act: -0.0001

Data Index: 1704323 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3464. Min Act: -0.0001

Data Index: 606545 (The Pile)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #19