< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 40 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.6523. Min Act: -0.0001

Data Index: 1507102 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.5181. Min Act: -0.0001

Data Index: 1571032 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.3038. Min Act: -0.0001

Data Index: 585328 (The Pile)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.3717. Min Act: -0.0001

Data Index: 1947577 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.1960. Min Act: -0.0001

Data Index: 189327 (The Pile)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.1649. Min Act: -0.0001

Data Index: 739634 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.0699. Min Act: -0.0001

Data Index: 447864 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.0837. Min Act: -0.0001

Data Index: 410112 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.0929. Min Act: -0.0001

Data Index: 831772 (The Pile)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.1519. Min Act: -0.0001

Data Index: 65395 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.0216. Min Act: -0.0001

Data Index: 256789 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.0393. Min Act: -0.0001

Data Index: 937255 (The Pile)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9732. Min Act: -0.0001

Data Index: 236072 (The Pile)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9921. Min Act: -0.0001

Data Index: 1569420 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9720. Min Act: -0.0001

Data Index: 981587 (The Pile)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9946. Min Act: -0.0001

Data Index: 1860915 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9887. Min Act: -0.0001

Data Index: 911681 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9265. Min Act: -0.0001

Data Index: 1829175 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9644. Min Act: -0.0001

Data Index: 1438382 (The Pile)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9829. Min Act: -0.0001

Data Index: 1688106 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #19