Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1462 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1024466 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1043. Min Act: -0.0002

Data Index: 944391 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1016. Min Act: -0.0002

Data Index: 274786 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1292012 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0991. Min Act: -0.0002

Data Index: 57700 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1311276 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0917. Min Act: -0.0002

Data Index: 247648 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1184822 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0876. Min Act: -0.0002

Data Index: 944925 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0925. Min Act: -0.0002

Data Index: 897360 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0920. Min Act: -0.0002

Data Index: 616877 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1346157 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0885. Min Act: -0.0002

Data Index: 746194 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0852. Min Act: -0.0001

Data Index: 65553 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0824. Min Act: -0.0002

Data Index: 363887 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0818. Min Act: -0.0002

Data Index: 631424 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0854. Min Act: -0.0002

Data Index: 55148 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0821. Min Act: -0.0002

Data Index: 3821 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1266218 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1051785 (C4 (Web Text))

Max Activating Token Index: 146