Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6059 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2259. Min Act: -0.0001

Data Index: 719565 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2013. Min Act: -0.0001

Data Index: 363195 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1978. Min Act: -0.0001

Data Index: 144639 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1155800 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1697. Min Act: -0.0001

Data Index: 343443 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1706. Min Act: -0.0001

Data Index: 706924 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1727. Min Act: -0.0001

Data Index: 17925 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1688. Min Act: -0.0001

Data Index: 643089 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1011025 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1049834 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1686. Min Act: -0.0001

Data Index: 197996 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1640. Min Act: -0.0001

Data Index: 537573 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1636. Min Act: -0.0001

Data Index: 347243 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1248590 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1347688 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1623. Min Act: -0.0001

Data Index: 753761 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1639. Min Act: -0.0001

Data Index: 1162860 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1195291 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1138266 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1332540 (C4 (Web Text))

Max Activating Token Index: 653