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

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

Neuron 4885 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: 0.2039. Min Range: -0.2039

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1143169 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1901. Min Act: -0.0000

Data Index: 630174 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1294566 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1234620 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1127496 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1742. Min Act: -0.0000

Data Index: 990808 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1232443 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1275808 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1669. Min Act: -0.0000

Data Index: 128791 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1534. Min Act: -0.0000

Data Index: 978601 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1514. Min Act: -0.0000

Data Index: 99622 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1358335 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1162450 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1400. Min Act: -0.0000

Data Index: 788667 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1442. Min Act: -0.0000

Data Index: 458376 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1490. Min Act: -0.0000

Data Index: 4926 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1204732 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1447. Min Act: -0.0000

Data Index: 726218 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1388. Min Act: -0.0000

Data Index: 718490 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1043945 (C4 (Web Text))

Max Activating Token Index: 452