< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2019 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: 3.5983. Min Range: -3.5983

Max Act: 3.4730. Min Act: -0.1700

Data Index: 1110863 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.4259. Min Act: -0.1700

Data Index: 2668641 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.3632. Min Act: -0.1700

Data Index: 7453480 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.5513. Min Act: -0.1699

Data Index: 9686364 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.5983. Min Act: -0.1700

Data Index: 1352098 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.3475. Min Act: -0.1699

Data Index: 7207610 (The Pile)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.4886. Min Act: -0.1700

Data Index: 7329289 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.2218. Min Act: -0.1700

Data Index: 5815517 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.3946. Min Act: -0.1691

Data Index: 7694795 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.4730. Min Act: -0.1700

Data Index: 115195 (The Pile)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.3161. Min Act: -0.1700

Data Index: 10137156 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.3475. Min Act: -0.1699

Data Index: 3465428 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.4573. Min Act: -0.1700

Data Index: 2856763 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.4102. Min Act: -0.1700

Data Index: 9539342 (The Pile)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.2061. Min Act: -0.1696

Data Index: 5201806 (The Pile)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.4102. Min Act: -0.1700

Data Index: 4767138 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.1274. Min Act: -0.1700

Data Index: 8296238 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.0643. Min Act: -0.1700

Data Index: 9117159 (The Pile)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.2061. Min Act: -0.1700

Data Index: 8734608 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5983. Min Range: -3.5983

Max Act: 3.0169. Min Act: -0.1700

Data Index: 9570851 (The Pile)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #19