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

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

Neuron 366 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1432374 (Python Code)

Max Activating Token Index: 832

Text #1

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1592559 (Python Code)

Max Activating Token Index: 584

Text #2

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1369988 (Python Code)

Max Activating Token Index: 746

Text #3

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1490518 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1497477 (Python Code)

Max Activating Token Index: 596

Text #5

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1476521 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1527523 (Python Code)

Max Activating Token Index: 307

Text #7

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1416999 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1485602 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1569339 (Python Code)

Max Activating Token Index: 476

Text #10

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1533902 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1582315 (Python Code)

Max Activating Token Index: 332

Text #12

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1619. Min Act: -0.0000

Data Index: 846920 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1647102 (Python Code)

Max Activating Token Index: 341

Text #14

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1121737 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1432295 (Python Code)

Max Activating Token Index: 647

Text #16

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1390055 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1436346 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1590808 (Python Code)

Max Activating Token Index: 457

Text #19

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1581428 (Python Code)

Max Activating Token Index: 15