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

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

Neuron 2498 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.3472. Min Act: -0.0000

Data Index: 411330 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0954. Min Act: -0.0000

Data Index: 615414 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1258757 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1261759 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0386. Min Act: -0.0000

Data Index: 102182 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0122. Min Act: -0.0000

Data Index: 102437 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0118. Min Act: -0.0000

Data Index: 881602 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9732. Min Act: -0.0000

Data Index: 713790 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9676. Min Act: -0.0000

Data Index: 992623 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9197. Min Act: -0.0000

Data Index: 43937 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1083449 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8870. Min Act: -0.0000

Data Index: 442161 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8806. Min Act: -0.0000

Data Index: 160496 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8586. Min Act: -0.0000

Data Index: 298617 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8871. Min Act: -0.0000

Data Index: 594941 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8089. Min Act: -0.0000

Data Index: 952589 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1323396 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8566. Min Act: -0.0000

Data Index: 50489 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8529. Min Act: -0.0000

Data Index: 307085 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8725. Min Act: -0.0000

Data Index: 124268 (C4 (Web Text))

Max Activating Token Index: 601