< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 10 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.8136. Min Act: -0.1688

Data Index: 9532525 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.5949. Min Act: -0.1677

Data Index: 2478572 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.5949. Min Act: -0.0193

Data Index: 2041623 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.4699. Min Act: -0.1081

Data Index: 2387038 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.8136. Min Act: -0.1700

Data Index: 6521452 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.5949. Min Act: -0.1462

Data Index: 9283315 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.5636. Min Act: -0.1487

Data Index: 6472472 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.6574. Min Act: -0.1698

Data Index: 8323393 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.5324. Min Act: -0.1646

Data Index: 4652116 (The Pile)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.7511. Min Act: -0.1699

Data Index: 5129399 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.5949. Min Act: -0.1700

Data Index: 9613769 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.6261. Min Act: -0.1660

Data Index: 10577377 (The Pile)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.4386. Min Act: -0.1700

Data Index: 5630344 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.7511. Min Act: -0.1699

Data Index: 1590480 (The Pile)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.5011. Min Act: -0.1694

Data Index: 7718655 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.4699. Min Act: -0.1700

Data Index: 4774773 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.4699. Min Act: -0.1699

Data Index: 322266 (The Pile)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.6886. Min Act: -0.1697

Data Index: 1086063 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.6886. Min Act: -0.1516

Data Index: 8227146 (The Pile)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.8136. Min Range: -4.8136

Max Act: 4.5949. Min Act: -0.1644

Data Index: 8333687 (The Pile)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #19