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

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

Neuron 5021 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6932. Min Range: -2.6932

Max Act: 2.6932. Min Act: -0.0000

Data Index: 1176821 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 2.6932. Min Range: -2.6932

Max Act: 2.3097. Min Act: -0.0000

Data Index: 612897 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 2.6932. Min Range: -2.6932

Max Act: 2.2986. Min Act: -0.0000

Data Index: 1333655 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 2.6932. Min Range: -2.6932

Max Act: 2.2273. Min Act: -0.0000

Data Index: 198904 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.9949. Min Act: -0.0000

Data Index: 466193 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 2.6932. Min Range: -2.6932

Max Act: 2.0977. Min Act: -0.0000

Data Index: 108364 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.8902. Min Act: -0.0000

Data Index: 503553 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.7833. Min Act: -0.0000

Data Index: 24853 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.8721. Min Act: -0.0000

Data Index: 968374 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.6474. Min Act: -0.0000

Data Index: 663538 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.6147. Min Act: -0.0000

Data Index: 846775 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.6008. Min Act: -0.0000

Data Index: 260919 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.5821. Min Act: -0.0000

Data Index: 1287003 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.5666. Min Act: -0.0000

Data Index: 509815 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.6610. Min Act: -0.0000

Data Index: 706564 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.6538. Min Act: -0.0000

Data Index: 642671 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.5453. Min Act: -0.0000

Data Index: 412863 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.5481. Min Act: -0.0000

Data Index: 1272955 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.5418. Min Act: -0.0000

Data Index: 542353 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 2.6932. Min Range: -2.6932

Max Act: 1.6338. Min Act: -0.0000

Data Index: 297135 (C4 (Web Text))

Max Activating Token Index: 149