< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2023 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.4471. Min Act: -0.1700

Data Index: 2806933 (The Pile)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.4314. Min Act: -0.1700

Data Index: 8452474 (The Pile)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.4314. Min Act: -0.1700

Data Index: 6588558 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.4471. Min Act: -0.1700

Data Index: 9543221 (The Pile)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.4000. Min Act: -0.1700

Data Index: 5691255 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3843. Min Act: -0.1700

Data Index: 10145248 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3843. Min Act: -0.1700

Data Index: 4648476 (The Pile)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3530. Min Act: -0.1700

Data Index: 6974093 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3530. Min Act: -0.1700

Data Index: 4453471 (The Pile)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3530. Min Act: -0.1700

Data Index: 6632309 (The Pile)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3373. Min Act: -0.1700

Data Index: 7097125 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3373. Min Act: -0.1700

Data Index: 1940531 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3216. Min Act: -0.1700

Data Index: 1238095 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3216. Min Act: -0.1700

Data Index: 5923739 (The Pile)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3216. Min Act: -0.1700

Data Index: 8091246 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3216. Min Act: -0.1700

Data Index: 1443748 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3059. Min Act: -0.1700

Data Index: 8953880 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3216. Min Act: -0.1700

Data Index: 7698694 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.3059. Min Act: -0.1700

Data Index: 6763051 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4471. Min Range: -3.4471

Max Act: 3.2902. Min Act: -0.1700

Data Index: 3886823 (The Pile)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #19