Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 201 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1528294 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1057723 (The Pile)

Max Activating Token Index: 426

Text #2

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7741. Min Act: -0.0000

Data Index: 309143 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7521. Min Act: -0.0000

Data Index: 548656 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1503773 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1589494 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7251. Min Act: -0.0000

Data Index: 68908 (The Pile)

Max Activating Token Index: 21

Text #7

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1074793 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1379241 (The Pile)

Max Activating Token Index: 690

Text #9

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1376382 (The Pile)

Max Activating Token Index: 692

Text #10

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1689545 (The Pile)

Max Activating Token Index: 75

Text #11

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7584. Min Act: -0.0000

Data Index: 232469 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1842081 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7074. Min Act: -0.0000

Data Index: 341572 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6736. Min Act: -0.0000

Data Index: 194780 (The Pile)

Max Activating Token Index: 339

Text #15

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1985033 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6642. Min Act: -0.0000

Data Index: 967025 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1361219 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6385. Min Act: -0.0000

Data Index: 340980 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1844078 (The Pile)

Max Activating Token Index: 727