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

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

Neuron 2599 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1106527 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1870. Min Act: -0.0001

Data Index: 912879 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1764. Min Act: -0.0001

Data Index: 921244 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1701. Min Act: -0.0001

Data Index: 714877 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1893. Min Act: -0.0001

Data Index: 18404 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1674. Min Act: -0.0001

Data Index: 1208018 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1742. Min Act: -0.0001

Data Index: 309345 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1475. Min Act: -0.0001

Data Index: 207328 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1100482 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1639. Min Act: -0.0001

Data Index: 1301340 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1524. Min Act: -0.0001

Data Index: 333626 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1269871 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1471. Min Act: -0.0001

Data Index: 838874 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1568. Min Act: -0.0001

Data Index: 1104915 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1608. Min Act: -0.0001

Data Index: 126615 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1631. Min Act: -0.0001

Data Index: 454763 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1588. Min Act: -0.0001

Data Index: 174586 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1267029 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1534. Min Act: -0.0001

Data Index: 34880 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1023878 (C4 (Web Text))

Max Activating Token Index: 706