< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5105 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.9198. Min Act: 0.0000

Data Index: 764060 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7442. Min Act: -0.0000

Data Index: 219723 (The Pile)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6997. Min Act: -0.0000

Data Index: 474654 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6943. Min Act: -0.0000

Data Index: 379218 (The Pile)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6933. Min Act: 0.0001

Data Index: 618757 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1746822 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1637319 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6193. Min Act: -0.0000

Data Index: 524407 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6140. Min Act: 0.0000

Data Index: 1597430 (The Pile)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6459. Min Act: -0.0000

Data Index: 903479 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1101060 (The Pile)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1553402 (The Pile)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6057. Min Act: -0.0000

Data Index: 64184 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5639. Min Act: 0.0000

Data Index: 1743973 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1515928 (The Pile)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5915. Min Act: 0.0000

Data Index: 1012245 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5574. Min Act: 0.0000

Data Index: 1536613 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5884. Min Act: -0.0000

Data Index: 67489 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5851. Min Act: -0.0000

Data Index: 90334 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5869. Min Act: 0.0000

Data Index: 1901951 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #19