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

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

Neuron 4872 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3618. Min Act: -0.0000

Data Index: 709293 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3735. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3854. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3386. Min Act: -0.0000

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3398. Min Act: -0.0000

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3327. Min Act: -0.0000

Data Index: 8886 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3204. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1130933 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2747. Min Act: -0.0000

Data Index: 686950 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1004508 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1285735 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2779. Min Act: -0.0000

Data Index: 501034 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2560. Min Act: -0.0000

Data Index: 299707 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2836. Min Act: -0.0000

Data Index: 398853 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2612. Min Act: -0.0000

Data Index: 499104 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1129556 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2516. Min Act: -0.0000

Data Index: 721483 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1232889 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1319559 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2639. Min Act: -0.0000

Data Index: 758150 (C4 (Web Text))

Max Activating Token Index: 702