< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 68 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4911. Min Act: -0.0004

Data Index: 1073838 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3864. Min Act: -0.0004

Data Index: 1881705 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4099. Min Act: -0.0005

Data Index: 312683 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4081. Min Act: -0.0004

Data Index: 736968 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3769. Min Act: -0.0004

Data Index: 389787 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3873. Min Act: -0.0004

Data Index: 983850 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3823. Min Act: -0.0004

Data Index: 210486 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3584. Min Act: -0.0004

Data Index: 392184 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3961. Min Act: -0.0004

Data Index: 237527 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3535. Min Act: -0.0004

Data Index: 790896 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3360. Min Act: -0.0004

Data Index: 137248 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3294. Min Act: -0.0004

Data Index: 984799 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3517. Min Act: -0.0004

Data Index: 775562 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3499. Min Act: -0.0004

Data Index: 218632 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3506. Min Act: -0.0004

Data Index: 1935393 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3477. Min Act: -0.0004

Data Index: 1560758 (The Pile)

Max Activating Token Index: 511

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3424. Min Act: -0.0004

Data Index: 1956380 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3612. Min Act: -0.0004

Data Index: 1641952 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3251. Min Act: -0.0004

Data Index: 1567297 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3324. Min Act: -0.0004

Data Index: 295229 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #19