< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 50 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.5685. Min Act: -0.0001

Data Index: 1613093 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.4879. Min Act: -0.0001

Data Index: 1056721 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.4167. Min Act: -0.0001

Data Index: 388072 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.3294. Min Act: -0.0001

Data Index: 1728785 (The Pile)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2987. Min Act: -0.0001

Data Index: 415450 (The Pile)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2659. Min Act: -0.0001

Data Index: 129495 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2930. Min Act: -0.0001

Data Index: 1805884 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.3354. Min Act: -0.0001

Data Index: 1802464 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2635. Min Act: -0.0001

Data Index: 680571 (The Pile)

Max Activating Token Index: 111

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2569. Min Act: -0.0001

Data Index: 767293 (The Pile)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.3789. Min Act: -0.0001

Data Index: 1404795 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2441. Min Act: -0.0001

Data Index: 1773723 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2060. Min Act: -0.0001

Data Index: 1290456 (The Pile)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2561. Min Act: -0.0001

Data Index: 876420 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2999. Min Act: -0.0001

Data Index: 1769269 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2702. Min Act: -0.0001

Data Index: 1956001 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1711. Min Act: -0.0001

Data Index: 684290 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.0951. Min Act: -0.0001

Data Index: 1883451 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1642. Min Act: -0.0001

Data Index: 228535 (The Pile)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1687. Min Act: -0.0001

Data Index: 21990 (The Pile)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #19