Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1298 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2829. Min Range: -2.2829

Max Act: 2.2829. Min Act: -0.0000

Data Index: 119388 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.9024. Min Act: -0.0000

Data Index: 160163 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.8419. Min Act: -0.0000

Data Index: 457668 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.6489. Min Act: -0.0000

Data Index: 747969 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.5563. Min Act: -0.0000

Data Index: 31974 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.5342. Min Act: -0.0000

Data Index: 673397 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.6184. Min Act: -0.0000

Data Index: 146281 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.6657. Min Act: -0.0000

Data Index: 961853 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.5332. Min Act: -0.0000

Data Index: 662049 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.4983. Min Act: -0.0000

Data Index: 198711 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.5567. Min Act: -0.0000

Data Index: 685758 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.4923. Min Act: -0.0000

Data Index: 292278 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.3711. Min Act: -0.0000

Data Index: 877055 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.4697. Min Act: -0.0000

Data Index: 738166 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.4870. Min Act: -0.0000

Data Index: 111215 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.3170. Min Act: -0.0000

Data Index: 763014 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.3412. Min Act: -0.0000

Data Index: 622213 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.3495. Min Act: -0.0000

Data Index: 936824 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.2962. Min Act: -0.0000

Data Index: 357687 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 2.2829. Min Range: -2.2829

Max Act: 1.3843. Min Act: -0.0000

Data Index: 980965 (C4 (Web Text))

Max Activating Token Index: 570