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

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

Neuron 4014 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6664. Min Act: -0.0001

Data Index: 80177 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1192103 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1264201 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5520. Min Act: -0.0000

Data Index: 356630 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1052254 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5542. Min Act: -0.0000

Data Index: 611172 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5479. Min Act: -0.0000

Data Index: 794491 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1354870 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5466. Min Act: -0.0000

Data Index: 835195 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1109160 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4932. Min Act: -0.0000

Data Index: 887367 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1137710 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4697. Min Act: -0.0000

Data Index: 242746 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4756. Min Act: -0.0000

Data Index: 791251 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4754. Min Act: -0.0001

Data Index: 913168 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4594. Min Act: -0.0000

Data Index: 50218 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4415. Min Act: -0.0000

Data Index: 863299 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4760. Min Act: -0.0000

Data Index: 156311 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1142806 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4382. Min Act: -0.0000

Data Index: 272615 (C4 (Web Text))

Max Activating Token Index: 422