< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 49 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.5057. Min Act: -0.0001

Data Index: 1596264 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.2903. Min Act: -0.0001

Data Index: 465117 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1226805 (The Pile)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.2984. Min Act: -0.0001

Data Index: 841306 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.1580. Min Act: -0.0001

Data Index: 919922 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.2659. Min Act: -0.0001

Data Index: 1048184 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.3048. Min Act: -0.0001

Data Index: 1954222 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5057. Min Range: -1.5057

Max Act: 0.9860. Min Act: -0.0001

Data Index: 496818 (The Pile)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.4098. Min Act: -0.0001

Data Index: 153354 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.1363. Min Act: -0.0001

Data Index: 925654 (The Pile)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.1836. Min Act: -0.0001

Data Index: 627969 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.1494. Min Act: -0.0001

Data Index: 1649485 (The Pile)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.0367. Min Act: -0.0001

Data Index: 835860 (The Pile)

Max Activating Token Index: 622

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.1601. Min Act: -0.0001

Data Index: 1388851 (The Pile)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.2076. Min Act: -0.0001

Data Index: 1084014 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.0229. Min Act: -0.0001

Data Index: 1605304 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.1863. Min Act: -0.0001

Data Index: 303642 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.0433. Min Act: -0.0001

Data Index: 1989588 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.1254. Min Act: -0.0001

Data Index: 1246415 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5057. Min Range: -1.5057

Max Act: 1.1437. Min Act: -0.0001

Data Index: 98059 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #19