< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4094 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: 2.0671. Min Range: -2.0671

Max Act: 2.0671. Min Act: -0.0001

Data Index: 1872990 (The Pile)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.7291. Min Act: -0.0001

Data Index: 1377923 (The Pile)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.2925. Min Act: -0.0001

Data Index: 737187 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.3937. Min Act: -0.0001

Data Index: 1595409 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.3965. Min Act: -0.0001

Data Index: 60296 (The Pile)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.4422. Min Act: -0.0001

Data Index: 1229349 (The Pile)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.3401. Min Act: -0.0001

Data Index: 584693 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.2566. Min Act: -0.0001

Data Index: 1742471 (The Pile)

Max Activating Token Index: 731

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.3202. Min Act: -0.0001

Data Index: 31421 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.1655. Min Act: -0.0001

Data Index: 347611 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.2114. Min Act: -0.0001

Data Index: 121418 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.2137. Min Act: -0.0001

Data Index: 1333044 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.2546. Min Act: -0.0001

Data Index: 1626666 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.1431. Min Act: -0.0001

Data Index: 767762 (The Pile)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.2777. Min Act: -0.0001

Data Index: 1317531 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.0671. Min Range: -2.0671

Max Act: 0.9966. Min Act: -0.0001

Data Index: 1503939 (The Pile)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.0791. Min Act: -0.0001

Data Index: 764071 (The Pile)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.1357. Min Act: -0.0001

Data Index: 1708321 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.0671. Min Range: -2.0671

Max Act: 1.1630. Min Act: -0.0000

Data Index: 898351 (The Pile)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.0671. Min Range: -2.0671

Max Act: 0.9848. Min Act: -0.0001

Data Index: 672268 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #19