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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 43 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.7787. Min Act: -0.0000

Data Index: 364032 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.7145. Min Act: -0.0000

Data Index: 123264 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.7141. Min Act: -0.0000

Data Index: 635166 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6768. Min Act: -0.0000

Data Index: 933932 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6477. Min Act: -0.0000

Data Index: 341767 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6282. Min Act: -0.0000

Data Index: 594434 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6514. Min Act: -0.0000

Data Index: 573379 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6043. Min Act: -0.0000

Data Index: 647710 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6101. Min Act: -0.0000

Data Index: 487640 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1233593 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6028. Min Act: -0.0000

Data Index: 21786 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6384. Min Act: -0.0000

Data Index: 371767 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6136. Min Act: -0.0000

Data Index: 684652 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6001. Min Act: -0.0000

Data Index: 138092 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5755. Min Act: -0.0000

Data Index: 792074 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1012315 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5889. Min Act: -0.0000

Data Index: 608744 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6029. Min Act: -0.0000

Data Index: 322721 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1115673 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5732. Min Act: -0.0000

Data Index: 833182 (C4 (Web Text))

Max Activating Token Index: 691