< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3047 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2939. Min Act: -0.0001

Data Index: 361314 (The Pile)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.3012. Min Act: -0.0001

Data Index: 1134117 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.3012. Min Act: -0.0001

Data Index: 1986468 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2911. Min Act: -0.0001

Data Index: 1102236 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2883. Min Act: -0.0001

Data Index: 1866918 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2866. Min Act: -0.0001

Data Index: 686465 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2873. Min Act: -0.0001

Data Index: 257759 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2862. Min Act: -0.0001

Data Index: 454604 (The Pile)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2849. Min Act: -0.0001

Data Index: 262093 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2756. Min Act: -0.0001

Data Index: 716316 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2854. Min Act: -0.0001

Data Index: 240861 (The Pile)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1226495 (The Pile)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1608410 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2831. Min Act: -0.0001

Data Index: 704537 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1959475 (The Pile)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2713. Min Act: -0.0001

Data Index: 1079476 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2803. Min Act: -0.0001

Data Index: 1984957 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2816. Min Act: -0.0001

Data Index: 499218 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2898. Min Act: -0.0001

Data Index: 916395 (The Pile)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2797. Min Act: -0.0001

Data Index: 1366955 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #19