< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4036 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: 0.5847. Min Range: -0.5847

Max Act: 0.5847. Min Act: -0.0001

Data Index: 1726644 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5007. Min Act: -0.0001

Data Index: 613296 (The Pile)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4905. Min Act: -0.0001

Data Index: 74665 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4804. Min Act: -0.0001

Data Index: 941141 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5197. Min Act: -0.0001

Data Index: 864862 (The Pile)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4907. Min Act: -0.0001

Data Index: 893763 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4813. Min Act: -0.0001

Data Index: 1335 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4490. Min Act: -0.0001

Data Index: 1335739 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4717. Min Act: -0.0001

Data Index: 1179986 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4484. Min Act: -0.0001

Data Index: 37994 (The Pile)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4684. Min Act: -0.0001

Data Index: 876839 (The Pile)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4502. Min Act: -0.0001

Data Index: 1817249 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4318. Min Act: -0.0001

Data Index: 452227 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4346. Min Act: -0.0001

Data Index: 1001869 (The Pile)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4572. Min Act: -0.0001

Data Index: 755916 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4338. Min Act: -0.0001

Data Index: 1012991 (The Pile)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4396. Min Act: -0.0001

Data Index: 844670 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4569. Min Act: -0.0001

Data Index: 506558 (The Pile)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4512. Min Act: -0.0001

Data Index: 1369862 (The Pile)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4229. Min Act: -0.0001

Data Index: 445273 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #19