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

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

Neuron 4354 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.9499. Min Act: -0.0000

Data Index: 270344 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.7564. Min Act: -0.0000

Data Index: 219444 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1227800 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.6441. Min Act: -0.0001

Data Index: 630196 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1052117 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.6684. Min Act: -0.0000

Data Index: 910168 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1204566 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.6688. Min Act: -0.0001

Data Index: 437380 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.5864. Min Act: -0.0000

Data Index: 941391 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1303622 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1159168 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.6337. Min Act: -0.0000

Data Index: 933612 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.6010. Min Act: -0.0000

Data Index: 780631 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1269428 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.6237. Min Act: -0.0000

Data Index: 959311 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.5488. Min Act: -0.0000

Data Index: 504860 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.5705. Min Act: -0.0000

Data Index: 379892 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.5814. Min Act: -0.0000

Data Index: 331581 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.5972. Min Act: -0.0000

Data Index: 647328 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.9499. Min Range: -0.9499

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1436527 (Python Code)

Max Activating Token Index: 464