< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 34 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.5070. Min Act: -0.1699

Data Index: 1884402 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4746. Min Act: -0.1700

Data Index: 518568 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4746. Min Act: -0.1686

Data Index: 3778061 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4746. Min Act: -0.1682

Data Index: 5811077 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4584. Min Act: -0.1699

Data Index: 5394017 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4584. Min Act: -0.1700

Data Index: 5662244 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4584. Min Act: -0.1699

Data Index: 10629070 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4584. Min Act: -0.1686

Data Index: 6206770 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4584. Min Act: -0.1674

Data Index: 9930309 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4584. Min Act: -0.1699

Data Index: 7718074 (The Pile)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4421. Min Act: -0.1700

Data Index: 1557256 (The Pile)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4421. Min Act: -0.1681

Data Index: 9834122 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4421. Min Act: -0.1700

Data Index: 3962773 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4421. Min Act: -0.1573

Data Index: 6619118 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4421. Min Act: -0.1670

Data Index: 553669 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4259. Min Act: -0.1611

Data Index: 1224907 (The Pile)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4259. Min Act: -0.1699

Data Index: 4642707 (The Pile)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4259. Min Act: -0.1687

Data Index: 4783124 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4259. Min Act: -0.1559

Data Index: 4907534 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.4259. Min Act: -0.1700

Data Index: 2419416 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #19