< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 2393 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.6283. Min Act: -0.0002

Data Index: 1043630 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.5529. Min Act: -0.0002

Data Index: 1945106 (The Pile)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.5229. Min Act: -0.0002

Data Index: 1031943 (The Pile)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.5165. Min Act: -0.0002

Data Index: 237063 (The Pile)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.5025. Min Act: -0.0002

Data Index: 407320 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4867. Min Act: -0.0002

Data Index: 568443 (The Pile)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4808. Min Act: -0.0002

Data Index: 1486375 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4841. Min Act: -0.0002

Data Index: 937115 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.5041. Min Act: -0.0002

Data Index: 1722630 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4844. Min Act: -0.0002

Data Index: 55771 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4826. Min Act: -0.0002

Data Index: 1588379 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4516. Min Act: -0.0002

Data Index: 1571353 (The Pile)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4848. Min Act: -0.0002

Data Index: 308368 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4594. Min Act: -0.0002

Data Index: 508938 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4518. Min Act: -0.0002

Data Index: 1774092 (The Pile)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4781. Min Act: -0.0002

Data Index: 1269022 (The Pile)

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4609. Min Act: -0.0002

Data Index: 1579551 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4529. Min Act: -0.0002

Data Index: 1032427 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4474. Min Act: -0.0002

Data Index: 1943316 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4585. Min Act: -0.0002

Data Index: 1644935 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #19