< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4095 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: 2.9750. Min Range: -2.9750

Max Act: 2.9750. Min Act: -0.0001

Data Index: 1797143 (The Pile)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.2757. Min Act: -0.0001

Data Index: 353093 (The Pile)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.4608. Min Act: -0.0001

Data Index: 1328212 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.5939. Min Act: -0.0001

Data Index: 893858 (The Pile)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.2740. Min Act: -0.0001

Data Index: 529422 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.1103. Min Act: -0.0001

Data Index: 1837894 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.0797. Min Act: -0.0001

Data Index: 661205 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.0370. Min Act: -0.0001

Data Index: 664476 (The Pile)

Max Activating Token Index: 511

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.0591. Min Act: -0.0001

Data Index: 1957524 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.0931. Min Act: -0.0001

Data Index: 1764328 (The Pile)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.2208. Min Act: -0.0001

Data Index: 718586 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.1234. Min Act: -0.0001

Data Index: 145344 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.0653. Min Act: -0.0001

Data Index: 1880736 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9750. Min Range: -2.9750

Max Act: 1.9432. Min Act: -0.0001

Data Index: 1653095 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.1470. Min Act: -0.0001

Data Index: 138922 (The Pile)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9750. Min Range: -2.9750

Max Act: 1.8975. Min Act: -0.0001

Data Index: 1734713 (The Pile)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9750. Min Range: -2.9750

Max Act: 2.1242. Min Act: -0.0001

Data Index: 1591118 (The Pile)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9750. Min Range: -2.9750

Max Act: 1.9932. Min Act: -0.0001

Data Index: 278860 (The Pile)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9750. Min Range: -2.9750

Max Act: 1.9667. Min Act: -0.0001

Data Index: 1252880 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9750. Min Range: -2.9750

Max Act: 1.8076. Min Act: -0.0001

Data Index: 267351 (The Pile)

Max Activating Token Index: 622

Click toggle to see full text

Truncated

Full Text #19