< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 31 in Layer 18

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.5746. Min Act: -0.1700

Data Index: 286102 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4179. Min Act: -0.1700

Data Index: 7265130 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4022. Min Act: -0.1700

Data Index: 4644277 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.3865. Min Act: -0.1700

Data Index: 7062927 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.3865. Min Act: -0.1700

Data Index: 9422400 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.3551. Min Act: -0.1699

Data Index: 3447511 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.3551. Min Act: -0.1700

Data Index: 6686407 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.3394. Min Act: -0.1700

Data Index: 1329973 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.3394. Min Act: -0.1700

Data Index: 9336330 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.3394. Min Act: -0.1700

Data Index: 4190662 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2923. Min Act: -0.1700

Data Index: 10061853 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2923. Min Act: -0.1700

Data Index: 5695099 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2766. Min Act: -0.1700

Data Index: 10640697 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2766. Min Act: -0.1700

Data Index: 2582510 (The Pile)

Max Activating Token Index: 497

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2452. Min Act: -0.1700

Data Index: 2582980 (The Pile)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2452. Min Act: -0.1700

Data Index: 2572952 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2452. Min Act: -0.1700

Data Index: 6320791 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2452. Min Act: -0.1700

Data Index: 3636335 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2295. Min Act: -0.1700

Data Index: 3046792 (The Pile)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.2295. Min Act: -0.1700

Data Index: 3390027 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #19