< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2394 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.3290. Min Act: -0.0002

Data Index: 587635 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2414. Min Act: -0.0002

Data Index: 1971263 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2138. Min Act: -0.0002

Data Index: 1922077 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2402. Min Act: -0.0002

Data Index: 880268 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.1923. Min Act: -0.0002

Data Index: 690649 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2617. Min Act: -0.0002

Data Index: 333700 (The Pile)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2057. Min Act: -0.0002

Data Index: 555037 (The Pile)

Max Activating Token Index: 981

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2044. Min Act: -0.0002

Data Index: 573950 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.1986. Min Act: -0.0002

Data Index: 1492461 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.1618. Min Act: -0.0002

Data Index: 173017 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2453. Min Act: -0.0002

Data Index: 1052481 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.1727. Min Act: -0.0002

Data Index: 1192034 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.1570. Min Act: -0.0002

Data Index: 955867 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.1480. Min Act: -0.0002

Data Index: 1265205 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.0793. Min Act: -0.0002

Data Index: 590817 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.1794. Min Act: -0.0002

Data Index: 947640 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2044. Min Act: -0.0002

Data Index: 1588147 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.1178. Min Act: -0.0002

Data Index: 230689 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.2261. Min Act: -0.0002

Data Index: 1151064 (The Pile)

Max Activating Token Index: 680

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.0782. Min Act: -0.0002

Data Index: 436913 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #19