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

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

Neuron 3657 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.9569. Min Act: -0.0001

Data Index: 556356 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.9883. Min Act: -0.0001

Data Index: 684614 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1326177 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8655. Min Act: -0.0001

Data Index: 440403 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.9560. Min Act: -0.0001

Data Index: 738162 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8185. Min Act: -0.0001

Data Index: 257121 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8014. Min Act: -0.0001

Data Index: 836730 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8075. Min Act: -0.0001

Data Index: 1031034 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7764. Min Act: -0.0001

Data Index: 146464 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8392. Min Act: -0.0001

Data Index: 569489 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8230. Min Act: -0.0001

Data Index: 1107294 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8925. Min Act: -0.0001

Data Index: 363105 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7756. Min Act: -0.0001

Data Index: 630513 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7215. Min Act: -0.0001

Data Index: 828596 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7449. Min Act: -0.0001

Data Index: 781860 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7797. Min Act: -0.0001

Data Index: 1238093 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6937. Min Act: -0.0001

Data Index: 1013535 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6960. Min Act: -0.0001

Data Index: 762488 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8093. Min Act: -0.0001

Data Index: 76817 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7795. Min Act: -0.0001

Data Index: 1096023 (C4 (Web Text))

Max Activating Token Index: 428