< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1161 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.3336. Min Act: -0.1700

Data Index: 1586370 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.3022. Min Act: -0.1699

Data Index: 2538900 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.3022. Min Act: -0.1700

Data Index: 10546366 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2550. Min Act: -0.1700

Data Index: 3263686 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2550. Min Act: -0.1684

Data Index: 71353 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2708. Min Act: -0.1700

Data Index: 10041011 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2550. Min Act: -0.1700

Data Index: 10627542 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2550. Min Act: -0.1700

Data Index: 1821025 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1454163 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1700

Data Index: 273412 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1696

Data Index: 267402 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1700

Data Index: 692823 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1699

Data Index: 721915 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1250226 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1700

Data Index: 982010 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1700

Data Index: 186512 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1700

Data Index: 222482 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1610735 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1685

Data Index: 328848 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3336. Min Range: -3.3336

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1386231 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19