< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 18 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.9162. Min Act: 0.0000

Data Index: 99643 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.9096. Min Act: 0.0000

Data Index: 1992686 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.9968. Min Act: 0.0001

Data Index: 1593616 (The Pile)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.9000. Min Act: 0.0000

Data Index: 1931327 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.7604. Min Act: -0.0000

Data Index: 781244 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.6126. Min Act: 0.0002

Data Index: 1585755 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.5204. Min Act: -0.0000

Data Index: 1463271 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.5952. Min Act: 0.0002

Data Index: 433237 (The Pile)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.6884. Min Act: 0.0001

Data Index: 1538722 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.5961. Min Act: 0.0001

Data Index: 270003 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.6587. Min Act: 0.0000

Data Index: 813274 (The Pile)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.5743. Min Act: -0.0000

Data Index: 665678 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.3913. Min Act: -0.0000

Data Index: 1615845 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.4805. Min Act: 0.0000

Data Index: 225984 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1694103 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.5468. Min Act: -0.0000

Data Index: 344082 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.4615. Min Act: 0.0000

Data Index: 265287 (The Pile)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.5107. Min Act: -0.0000

Data Index: 1596535 (The Pile)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.5022. Min Act: -0.0000

Data Index: 1247779 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.5091. Min Act: 0.0000

Data Index: 1313040 (The Pile)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #19