< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 7 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: 2.8489. Min Range: -2.8489

Max Act: 2.8489. Min Act: -0.1700

Data Index: 7077437 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.8012. Min Act: -0.1699

Data Index: 2225743 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7374. Min Act: -0.1700

Data Index: 1357263 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.8171. Min Act: -0.1700

Data Index: 6411606 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7534. Min Act: -0.1700

Data Index: 9055634 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7214. Min Act: -0.1700

Data Index: 1313816 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7214. Min Act: -0.1693

Data Index: 6165039 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7214. Min Act: -0.1699

Data Index: 8253299 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7374. Min Act: -0.1700

Data Index: 1414236 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.6894. Min Act: -0.1700

Data Index: 9496998 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7693. Min Act: -0.1699

Data Index: 5079223 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.6894. Min Act: -0.1681

Data Index: 9092031 (The Pile)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7214. Min Act: -0.1700

Data Index: 7850306 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7054. Min Act: -0.1699

Data Index: 5346097 (The Pile)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7054. Min Act: -0.1698

Data Index: 50887 (The Pile)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7054. Min Act: -0.1698

Data Index: 8700245 (The Pile)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7374. Min Act: -0.1700

Data Index: 2732740 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7054. Min Act: -0.1700

Data Index: 4495439 (The Pile)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.6894. Min Act: -0.1697

Data Index: 9260224 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8489. Min Range: -2.8489

Max Act: 2.7214. Min Act: -0.1699

Data Index: 6506297 (The Pile)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #19