< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 53 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8930. Min Act: -0.0001

Data Index: 347640 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0780. Min Range: -1.0780

Max Act: 1.0780. Min Act: -0.0001

Data Index: 1580956 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0780. Min Range: -1.0780

Max Act: 1.0324. Min Act: -0.0001

Data Index: 767436 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8888. Min Act: -0.0001

Data Index: 1933878 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8110. Min Act: -0.0001

Data Index: 1056865 (The Pile)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8917. Min Act: -0.0001

Data Index: 1125732 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8354. Min Act: -0.0001

Data Index: 872551 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8735. Min Act: -0.0001

Data Index: 1013667 (The Pile)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.9052. Min Act: -0.0001

Data Index: 51147 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8069. Min Act: -0.0001

Data Index: 1617975 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8037. Min Act: -0.0001

Data Index: 963985 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8372. Min Act: -0.0001

Data Index: 1154859 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8141. Min Act: -0.0001

Data Index: 151910 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8102. Min Act: -0.0001

Data Index: 345559 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.7831. Min Act: -0.0001

Data Index: 1784367 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.7768. Min Act: -0.0001

Data Index: 744975 (The Pile)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.8031. Min Act: -0.0001

Data Index: 1958413 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1421414 (The Pile)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.7112. Min Act: -0.0001

Data Index: 429746 (The Pile)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0780. Min Range: -1.0780

Max Act: 0.7550. Min Act: -0.0001

Data Index: 112760 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #19