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

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

Neuron 4378 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: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1237368 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1120149 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1056406 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0770. Min Act: -0.0001

Data Index: 502825 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1125020 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0760. Min Act: -0.0001

Data Index: 914980 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0711. Min Act: -0.0001

Data Index: 537850 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0728. Min Act: -0.0001

Data Index: 609058 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0691. Min Act: -0.0001

Data Index: 478208 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1108246 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0708. Min Act: -0.0001

Data Index: 111361 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1355162 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0694. Min Act: -0.0001

Data Index: 73422 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0732. Min Act: -0.0001

Data Index: 308187 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1320690 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0701. Min Act: -0.0001

Data Index: 456374 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0680. Min Act: -0.0001

Data Index: 673859 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0681. Min Act: -0.0001

Data Index: 249551 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0678. Min Act: -0.0001

Data Index: 57069 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0657. Min Act: -0.0001

Data Index: 649099 (C4 (Web Text))

Max Activating Token Index: 489