< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 18 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.4309. Min Act: -0.1700

Data Index: 8261656 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.3838. Min Act: -0.1700

Data Index: 1448948 (The Pile)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.3681. Min Act: -0.1700

Data Index: 8100687 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.3524. Min Act: -0.1700

Data Index: 4078010 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.3367. Min Act: -0.1700

Data Index: 9932965 (The Pile)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.3367. Min Act: -0.1700

Data Index: 2885242 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.3367. Min Act: -0.1700

Data Index: 10388086 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.3053. Min Act: -0.1700

Data Index: 1301472 (The Pile)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.3053. Min Act: -0.1700

Data Index: 7027913 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2896. Min Act: -0.1700

Data Index: 9209899 (The Pile)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2739. Min Act: -0.1700

Data Index: 4050370 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2582. Min Act: -0.1699

Data Index: 10086400 (The Pile)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2582. Min Act: -0.1700

Data Index: 7655852 (The Pile)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2582. Min Act: -0.1700

Data Index: 10725522 (The Pile)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2582. Min Act: -0.1700

Data Index: 6523625 (The Pile)

Max Activating Token Index: 894

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2582. Min Act: -0.1700

Data Index: 10053569 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2425. Min Act: -0.1700

Data Index: 5853706 (The Pile)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2425. Min Act: -0.1700

Data Index: 3253293 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2425. Min Act: -0.1700

Data Index: 4776196 (The Pile)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2268. Min Act: -0.1700

Data Index: 2904306 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #19