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

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

Neuron 1697 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2670. Min Act: -0.0002

Data Index: 1154979 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2272. Min Act: -0.0002

Data Index: 520383 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1941. Min Act: -0.0002

Data Index: 136480 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1996. Min Act: -0.0002

Data Index: 933693 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1920. Min Act: -0.0002

Data Index: 658451 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1911. Min Act: -0.0002

Data Index: 90613 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1637. Min Act: -0.0002

Data Index: 103307 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1680. Min Act: -0.0002

Data Index: 886033 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1643. Min Act: -0.0002

Data Index: 894862 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1589. Min Act: -0.0002

Data Index: 990296 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1652. Min Act: -0.0002

Data Index: 1199448 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1568. Min Act: -0.0002

Data Index: 225765 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1544. Min Act: -0.0002

Data Index: 331151 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1495. Min Act: -0.0002

Data Index: 1200741 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1461. Min Act: -0.0002

Data Index: 1041725 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1487. Min Act: -0.0002

Data Index: 1095476 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1306. Min Act: -0.0002

Data Index: 1156232 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1508. Min Act: -0.0002

Data Index: 1347143 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1431. Min Act: -0.0002

Data Index: 315831 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1333822 (C4 (Web Text))

Max Activating Token Index: 482