Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3395 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1077. Min Act: -0.0001

Data Index: 968563 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0825. Min Act: -0.0001

Data Index: 666866 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0905. Min Act: -0.0001

Data Index: 229760 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0775. Min Act: -0.0001

Data Index: 414463 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0817. Min Act: -0.0001

Data Index: 777900 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0826. Min Act: -0.0001

Data Index: 251047 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0760. Min Act: -0.0001

Data Index: 471391 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1096096 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1352388 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0719. Min Act: -0.0001

Data Index: 46270 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1064398 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0700. Min Act: -0.0001

Data Index: 247947 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0695. Min Act: -0.0001

Data Index: 203440 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1304805 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0673. Min Act: -0.0001

Data Index: 166641 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1221733 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0721. Min Act: -0.0001

Data Index: 904288 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0623. Min Act: -0.0001

Data Index: 204947 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0648. Min Act: -0.0001

Data Index: 183025 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0622. Min Act: -0.0001

Data Index: 388458 (C4 (Web Text))

Max Activating Token Index: 271