Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2242 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2307. Min Act: -0.0001

Data Index: 935046 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2226. Min Act: -0.0001

Data Index: 504036 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2030. Min Act: -0.0001

Data Index: 1572006 (Python Code)

Max Activating Token Index: 752

Text #3

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1610. Min Act: -0.0001

Data Index: 659722 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1789. Min Act: -0.0001

Data Index: 361026 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1827. Min Act: -0.0001

Data Index: 38992 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1601. Min Act: -0.0001

Data Index: 698863 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1059037 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1788. Min Act: -0.0001

Data Index: 1442027 (Python Code)

Max Activating Token Index: 144

Text #9

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1141001 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1491. Min Act: -0.0001

Data Index: 944096 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1535. Min Act: -0.0001

Data Index: 518877 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1528. Min Act: -0.0001

Data Index: 778295 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1585. Min Act: -0.0001

Data Index: 876994 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1506. Min Act: -0.0001

Data Index: 351829 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1719. Min Act: -0.0001

Data Index: 557056 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1577738 (Python Code)

Max Activating Token Index: 277

Text #17

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1677. Min Act: -0.0001

Data Index: 185046 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1589. Min Act: -0.0001

Data Index: 199809 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1610. Min Act: -0.0001

Data Index: 656331 (C4 (Web Text))

Max Activating Token Index: 137