< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 8 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4927. Min Act: -0.0001

Data Index: 437348 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4686. Min Act: -0.0001

Data Index: 749390 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4146. Min Act: -0.0001

Data Index: 1076131 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3744. Min Act: -0.0001

Data Index: 426984 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3717. Min Act: -0.0001

Data Index: 1131853 (The Pile)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2795. Min Act: -0.0001

Data Index: 85671 (The Pile)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.0762. Min Act: -0.0001

Data Index: 1515638 (The Pile)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2011. Min Act: -0.0001

Data Index: 962005 (The Pile)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.1919. Min Act: -0.0000

Data Index: 1434265 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.0693. Min Act: -0.0001

Data Index: 1863883 (The Pile)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3561. Min Act: -0.0001

Data Index: 111067 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2648. Min Act: -0.0001

Data Index: 703639 (The Pile)

Max Activating Token Index: 640

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3582. Min Act: -0.0001

Data Index: 1467539 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3812. Min Act: -0.0001

Data Index: 880268 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2734. Min Act: -0.0001

Data Index: 498603 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2603. Min Act: -0.0001

Data Index: 1094361 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.1504. Min Act: -0.0001

Data Index: 1448479 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2236. Min Act: -0.0001

Data Index: 294975 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3276. Min Act: -0.0001

Data Index: 916422 (The Pile)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2323. Min Act: -0.0001

Data Index: 1621991 (The Pile)

Max Activating Token Index: 907

Click toggle to see full text

Truncated

Full Text #19