< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 8 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: 1.2755. Min Range: -1.2755

Max Act: 1.2602. Min Act: -0.0001

Data Index: 1683780 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.2606. Min Act: -0.0001

Data Index: 1110865 (The Pile)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.1587. Min Act: -0.0001

Data Index: 1430276 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.2165. Min Act: -0.0001

Data Index: 61391 (The Pile)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.2755. Min Act: -0.0001

Data Index: 1270225 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.1610. Min Act: -0.0001

Data Index: 468374 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.2595. Min Act: -0.0001

Data Index: 1152065 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.1634. Min Act: -0.0001

Data Index: 1911756 (The Pile)

Max Activating Token Index: 90

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.0922. Min Act: -0.0001

Data Index: 1869045 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.1438. Min Act: -0.0001

Data Index: 499237 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.1916. Min Act: -0.0001

Data Index: 1966278 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.2755. Min Range: -1.2755

Max Act: 0.9742. Min Act: -0.0001

Data Index: 1406933 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.1258. Min Act: -0.0001

Data Index: 1728274 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.1221. Min Act: -0.0001

Data Index: 837479 (The Pile)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.0878. Min Act: -0.0001

Data Index: 346233 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.0963. Min Act: -0.0001

Data Index: 1471681 (The Pile)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.1043. Min Act: -0.0001

Data Index: 784064 (The Pile)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.2755. Min Range: -1.2755

Max Act: 0.9868. Min Act: -0.0001

Data Index: 1262266 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.0890. Min Act: -0.0001

Data Index: 1225666 (The Pile)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.2755. Min Range: -1.2755

Max Act: 1.0151. Min Act: -0.0001

Data Index: 116066 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #19