< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2043 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0713. Min Act: -0.1700

Data Index: 2137931 (The Pile)

Max Activating Token Index: 765

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.3213. Min Act: -0.1700

Data Index: 10025651 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.1338. Min Act: -0.1700

Data Index: 4180826 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.3213. Min Range: -4.3213

Max Act: 3.9775. Min Act: -0.1700

Data Index: 10654652 (The Pile)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.3213. Min Range: -4.3213

Max Act: 3.9775. Min Act: -0.1700

Data Index: 5866808 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0400. Min Act: -0.1700

Data Index: 1143003 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0713. Min Act: -0.1700

Data Index: 7766190 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0400. Min Act: -0.1700

Data Index: 2862592 (The Pile)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0087. Min Act: -0.1700

Data Index: 9494703 (The Pile)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0713. Min Act: -0.1700

Data Index: 4920486 (The Pile)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0400. Min Act: -0.1700

Data Index: 527515 (The Pile)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0400. Min Act: -0.1700

Data Index: 10000663 (The Pile)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0713. Min Act: -0.1700

Data Index: 6869267 (The Pile)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0087. Min Act: -0.1700

Data Index: 7369618 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0087. Min Act: -0.1700

Data Index: 7777358 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.3213. Min Range: -4.3213

Max Act: 3.9775. Min Act: -0.1700

Data Index: 9486237 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.3213. Min Range: -4.3213

Max Act: 3.8524. Min Act: -0.1700

Data Index: 5789173 (The Pile)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.3213. Min Range: -4.3213

Max Act: 4.0400. Min Act: -0.1700

Data Index: 3790098 (The Pile)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.3213. Min Range: -4.3213

Max Act: 3.9775. Min Act: -0.1700

Data Index: 1802858 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.3213. Min Range: -4.3213

Max Act: 3.9149. Min Act: -0.1700

Data Index: 3405161 (The Pile)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #19