< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5108 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: 2.4697. Min Range: -2.4697

Max Act: 2.4697. Min Act: -0.0001

Data Index: 1175830 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.4697. Min Range: -2.4697

Max Act: 2.0394. Min Act: -0.0001

Data Index: 1898660 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.4697. Min Range: -2.4697

Max Act: 2.0211. Min Act: -0.0001

Data Index: 1332559 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.4697. Min Range: -2.4697

Max Act: 2.1879. Min Act: -0.0001

Data Index: 1123754 (The Pile)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.4697. Min Range: -2.4697

Max Act: 2.2952. Min Act: -0.0001

Data Index: 9230 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.4697. Min Range: -2.4697

Max Act: 2.0858. Min Act: -0.0001

Data Index: 206820 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.4697. Min Range: -2.4697

Max Act: 2.0914. Min Act: -0.0001

Data Index: 442573 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.4697. Min Range: -2.4697

Max Act: 2.0093. Min Act: -0.0001

Data Index: 120159 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.4697. Min Range: -2.4697

Max Act: 2.0158. Min Act: -0.0001

Data Index: 1623819 (The Pile)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.9048. Min Act: -0.0001

Data Index: 192918 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.8676. Min Act: -0.0001

Data Index: 516006 (The Pile)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.4697. Min Range: -2.4697

Max Act: 2.0966. Min Act: -0.0001

Data Index: 1308747 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.9338. Min Act: -0.0001

Data Index: 1673997 (The Pile)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.8549. Min Act: -0.0001

Data Index: 1927855 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.8585. Min Act: -0.0001

Data Index: 163378 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.8067. Min Act: -0.0001

Data Index: 216403 (The Pile)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.8774. Min Act: -0.0001

Data Index: 1192037 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.8204. Min Act: -0.0001

Data Index: 7285 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.6134. Min Act: -0.0001

Data Index: 909815 (The Pile)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.4697. Min Range: -2.4697

Max Act: 1.5737. Min Act: -0.0001

Data Index: 970834 (The Pile)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #19