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

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

Neuron 1668 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: 0.2434. Min Range: -0.2434

Max Act: 0.2434. Min Act: -0.0000

Data Index: 916131 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2271. Min Act: -0.0000

Data Index: 389213 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2263. Min Act: -0.0000

Data Index: 513268 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1051327 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1341048 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1815. Min Act: -0.0000

Data Index: 3887 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1796. Min Act: -0.0000

Data Index: 139647 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1842. Min Act: -0.0000

Data Index: 500020 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1881. Min Act: -0.0000

Data Index: 777859 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1691. Min Act: -0.0000

Data Index: 887318 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1809. Min Act: -0.0000

Data Index: 565607 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1504. Min Act: -0.0000

Data Index: 834936 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1694. Min Act: -0.0000

Data Index: 856340 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1290. Min Act: -0.0000

Data Index: 506137 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1603. Min Act: -0.0000

Data Index: 720997 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1501. Min Act: -0.0000

Data Index: 681728 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1074999 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1575. Min Act: -0.0000

Data Index: 799621 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1618. Min Act: -0.0000

Data Index: 122327 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1728. Min Act: -0.0000

Data Index: 725845 (C4 (Web Text))

Max Activating Token Index: 797