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

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

Neuron 645 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: 0.2003. Min Range: -0.2003

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1536366 (Python Code)

Max Activating Token Index: 383

Text #1

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1365753 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1803. Min Act: -0.0001

Data Index: 1423064 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1415377 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1530289 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1440021 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1594865 (Python Code)

Max Activating Token Index: 262

Text #7

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1538098 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1487022 (Python Code)

Max Activating Token Index: 255

Text #9

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1556684 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1505771 (Python Code)

Max Activating Token Index: 527

Text #11

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1634560 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1364598 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1406772 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1584006 (Python Code)

Max Activating Token Index: 666

Text #15

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1464126 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1447947 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1541389 (Python Code)

Max Activating Token Index: 856

Text #18

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1361064 (Python Code)

Max Activating Token Index: 423

Text #19

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1638052 (Python Code)

Max Activating Token Index: 8