< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 13 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1101492 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.6863. Min Act: -0.0000

Data Index: 14421 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.7153. Min Act: -0.0000

Data Index: 1363800 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.5940. Min Act: -0.0000

Data Index: 253966 (The Pile)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.5850. Min Act: -0.0000

Data Index: 646448 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1563743 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.4977. Min Act: -0.0000

Data Index: 1056171 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1414068 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.5166. Min Act: -0.0000

Data Index: 402367 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.5632. Min Act: 0.0000

Data Index: 431437 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.4943. Min Act: -0.0000

Data Index: 866841 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.4487. Min Act: 0.0000

Data Index: 830611 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.5046. Min Act: -0.0000

Data Index: 858884 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1513060 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.3553. Min Act: -0.0000

Data Index: 1545096 (The Pile)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.4222. Min Act: -0.0000

Data Index: 690269 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1491008 (The Pile)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.3974. Min Act: -0.0000

Data Index: 742714 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1173100 (The Pile)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7153. Min Range: -1.7153

Max Act: 1.3876. Min Act: -0.0000

Data Index: 745547 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #19