< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 58 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: 1.1574. Min Range: -1.1574

Max Act: 1.0916. Min Act: -0.0000

Data Index: 247787 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0638. Min Act: -0.0000

Data Index: 252084 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.1574. Min Act: -0.0000

Data Index: 1680152 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0292. Min Act: -0.0001

Data Index: 324081 (The Pile)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8308. Min Act: -0.0000

Data Index: 281095 (The Pile)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0227. Min Act: -0.0000

Data Index: 882050 (The Pile)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0647. Min Act: -0.0001

Data Index: 945164 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9824. Min Act: -0.0001

Data Index: 1323567 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9482. Min Act: -0.0001

Data Index: 230544 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9986. Min Act: -0.0000

Data Index: 463577 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0140. Min Act: -0.0000

Data Index: 505039 (The Pile)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1768107 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9388. Min Act: -0.0001

Data Index: 416745 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9262. Min Act: -0.0001

Data Index: 366982 (The Pile)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9121. Min Act: -0.0001

Data Index: 358486 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0369. Min Act: -0.0001

Data Index: 68737 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9182. Min Act: -0.0001

Data Index: 72930 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9120. Min Act: -0.0001

Data Index: 485579 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8527. Min Act: -0.0000

Data Index: 776319 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1869945 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #19