< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 9 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.5100. Min Act: -0.0001

Data Index: 154475 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.4793. Min Act: -0.0001

Data Index: 1868808 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2795. Min Act: -0.0001

Data Index: 1547970 (The Pile)

Max Activating Token Index: 551

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2630. Min Act: -0.0001

Data Index: 1359737 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1206. Min Act: -0.0001

Data Index: 235837 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1271. Min Act: -0.0001

Data Index: 1146633 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1411. Min Act: -0.0001

Data Index: 1308929 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1599. Min Act: -0.0001

Data Index: 110113 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1875. Min Act: -0.0001

Data Index: 1653771 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1512. Min Act: -0.0001

Data Index: 422720 (The Pile)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1947. Min Act: -0.0001

Data Index: 72390 (The Pile)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0995. Min Act: -0.0001

Data Index: 353352 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1069. Min Act: -0.0001

Data Index: 504600 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1258. Min Act: -0.0001

Data Index: 1119299 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0940. Min Act: -0.0001

Data Index: 562911 (The Pile)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5100. Min Range: -1.5100

Max Act: 0.9996. Min Act: -0.0001

Data Index: 234952 (The Pile)

Max Activating Token Index: 797

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5100. Min Range: -1.5100

Max Act: 0.9967. Min Act: -0.0001

Data Index: 440277 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1151. Min Act: -0.0001

Data Index: 1486424 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5100. Min Range: -1.5100

Max Act: 0.8067. Min Act: -0.0001

Data Index: 1056777 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0537. Min Act: -0.0001

Data Index: 1963895 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #19