< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 15 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: 1.0064. Min Range: -1.0064

Max Act: 1.0064. Min Act: -0.0001

Data Index: 669812 (The Pile)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9525. Min Act: -0.0001

Data Index: 79709 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9540. Min Act: -0.0001

Data Index: 1698282 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9300. Min Act: -0.0001

Data Index: 1288806 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9642. Min Act: -0.0001

Data Index: 1930392 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9001. Min Act: -0.0001

Data Index: 1743375 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8635. Min Act: -0.0001

Data Index: 905067 (The Pile)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8705. Min Act: -0.0001

Data Index: 668539 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9072. Min Act: -0.0001

Data Index: 425351 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8495. Min Act: -0.0001

Data Index: 747971 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1496064 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8544. Min Act: -0.0001

Data Index: 1391939 (The Pile)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8046. Min Act: -0.0001

Data Index: 566998 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8447. Min Act: -0.0001

Data Index: 1332769 (The Pile)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8058. Min Act: -0.0001

Data Index: 1968703 (The Pile)

Max Activating Token Index: 967

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.6815. Min Act: -0.0001

Data Index: 1933181 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1398411 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7845. Min Act: -0.0001

Data Index: 1917946 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7445. Min Act: -0.0001

Data Index: 114261 (The Pile)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7157. Min Act: -0.0001

Data Index: 395268 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #19