Model: None

Dataset: The Pile

Neuron 2663 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')

Text #0

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.1109. Min Act: -0.1700

Data Index: 1488135 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0952. Min Act: -0.1700

Data Index: 10357674 (The Pile)

Max Activating Token Index: 751

Text #2

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0952. Min Act: -0.1700

Data Index: 7071298 (The Pile)

Max Activating Token Index: 675

Text #3

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0794. Min Act: -0.1700

Data Index: 8006438 (The Pile)

Max Activating Token Index: 954

Text #4

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0794. Min Act: -0.1700

Data Index: 9033962 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0794. Min Act: -0.1700

Data Index: 7919355 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0794. Min Act: -0.1700

Data Index: 486472 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0794. Min Act: -0.1700

Data Index: 2013864 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0636. Min Act: -0.1700

Data Index: 7228098 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0636. Min Act: -0.1700

Data Index: 9191473 (The Pile)

Max Activating Token Index: 401

Text #10

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0636. Min Act: -0.1700

Data Index: 8712122 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0636. Min Act: -0.1700

Data Index: 1586160 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0636. Min Act: -0.1700

Data Index: 6165183 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0478. Min Act: -0.1700

Data Index: 9312208 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0478. Min Act: -0.1700

Data Index: 8013003 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0478. Min Act: -0.1700

Data Index: 5899171 (The Pile)

Max Activating Token Index: 652

Text #16

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0320. Min Act: -0.1700

Data Index: 5004534 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0320. Min Act: -0.1700

Data Index: 1160356 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0320. Min Act: -0.1700

Data Index: 1862159 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0162. Min Act: -0.1700

Data Index: 7768663 (The Pile)

Max Activating Token Index: 497