< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 18 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: 3.9553. Min Range: -3.9553

Max Act: 3.6111. Min Act: -0.1700

Data Index: 988383 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.9553. Min Act: -0.1698

Data Index: 1014819 (The Pile)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.6268. Min Act: -0.1698

Data Index: 7031975 (The Pile)

Max Activating Token Index: 422

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.4702. Min Act: -0.1696

Data Index: 288363 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.5485. Min Act: -0.1700

Data Index: 4893171 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.2662. Min Act: -0.1700

Data Index: 8659932 (The Pile)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.4702. Min Act: -0.1699

Data Index: 9330162 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.2662. Min Act: -0.1700

Data Index: 2803324 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.3918. Min Act: -0.1700

Data Index: 6401137 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.5642. Min Act: -0.1700

Data Index: 5391443 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.7989. Min Act: -0.1700

Data Index: 7006436 (The Pile)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.6424. Min Act: -0.1699

Data Index: 3133242 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.2190. Min Act: -0.1699

Data Index: 1867249 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.3604. Min Act: -0.1700

Data Index: 8762283 (The Pile)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.5172. Min Act: -0.1700

Data Index: 5910917 (The Pile)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.4702. Min Act: -0.1700

Data Index: 9484241 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.3447. Min Act: -0.1550

Data Index: 5769882 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.4858. Min Act: -0.1700

Data Index: 655473 (The Pile)

Max Activating Token Index: 409

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.6424. Min Act: -0.1698

Data Index: 1716450 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.3918. Min Act: -0.1700

Data Index: 227395 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #19