< Prev | Home | Model | Random | Next >

Model: SoLU Model: 2 Layers, 2944 Neurons per Layer

Dataset: The Pile

Neuron 1 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')



Text #0

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1316847 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1183196 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0003

Data Index: 393998 (The Pile)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 958686 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 949966 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1369509 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0003

Data Index: 129698 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1649164 (The Pile)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1237613 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1175298 (The Pile)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0003

Data Index: 862548 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0003

Data Index: 913448 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1241324 (The Pile)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0003

Data Index: 436882 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0003

Data Index: 395974 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1126299 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1673499 (The Pile)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1852712 (The Pile)

Max Activating Token Index: 296

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 924776 (The Pile)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1146326 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #19