< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2031 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.4124. Min Act: -0.1700

Data Index: 2597753 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3811. Min Act: -0.1700

Data Index: 10528266 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3811. Min Act: -0.1699

Data Index: 8292039 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2249. Min Act: -0.1699

Data Index: 3581230 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2874. Min Act: -0.1700

Data Index: 2259857 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.0999. Min Act: -0.1699

Data Index: 7697520 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.1311. Min Act: -0.1700

Data Index: 5826365 (The Pile)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3186. Min Act: -0.1700

Data Index: 7015228 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.1311. Min Act: -0.1700

Data Index: 3639791 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.1311. Min Act: -0.1700

Data Index: 6864798 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2561. Min Act: -0.1700

Data Index: 2850166 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.1624. Min Act: -0.1700

Data Index: 10102981 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.0999. Min Act: -0.1700

Data Index: 5280177 (The Pile)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3499. Min Act: -0.1700

Data Index: 6291625 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2874. Min Act: -0.1700

Data Index: 6775072 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.1936. Min Act: -0.1700

Data Index: 6454526 (The Pile)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3499. Min Act: -0.1700

Data Index: 4252865 (The Pile)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2874. Min Act: -0.1700

Data Index: 4535035 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2249. Min Act: -0.1700

Data Index: 3420403 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2561. Min Act: -0.1700

Data Index: 6294955 (The Pile)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #19