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

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

Neuron 2345 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1650. Min Range: -3.1650

Max Act: 3.1642. Min Act: -0.0000

Data Index: 1405006 (Python Code)

Max Activating Token Index: 996

Text #1

Max Range: 3.1650. Min Range: -3.1650

Max Act: 3.1650. Min Act: -0.0000

Data Index: 1423611 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9931. Min Act: 0.0001

Data Index: 1369223 (Python Code)

Max Activating Token Index: 66

Text #3

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9562. Min Act: -0.0000

Data Index: 1372990 (Python Code)

Max Activating Token Index: 333

Text #4

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9097. Min Act: 0.0000

Data Index: 1398299 (Python Code)

Max Activating Token Index: 663

Text #5

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.8572. Min Act: -0.0000

Data Index: 1641731 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.6710. Min Act: -0.0000

Data Index: 1576851 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.2807. Min Act: -0.0000

Data Index: 1653481 (Python Code)

Max Activating Token Index: 734

Text #8

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.7850. Min Act: -0.0000

Data Index: 1368256 (Python Code)

Max Activating Token Index: 360

Text #9

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.5949. Min Act: -0.0000

Data Index: 1606517 (Python Code)

Max Activating Token Index: 617

Text #10

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.4507. Min Act: -0.0000

Data Index: 1644099 (Python Code)

Max Activating Token Index: 915

Text #11

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.3668. Min Act: -0.0000

Data Index: 1456579 (Python Code)

Max Activating Token Index: 301

Text #12

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.3312. Min Act: -0.0000

Data Index: 1389860 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.3494. Min Act: 0.0000

Data Index: 1548631 (Python Code)

Max Activating Token Index: 103

Text #14

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.4501. Min Act: -0.0000

Data Index: 1495628 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.4182. Min Act: -0.0000

Data Index: 1469275 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.2751. Min Act: -0.0000

Data Index: 1425953 (Python Code)

Max Activating Token Index: 676

Text #17

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.2693. Min Act: -0.0000

Data Index: 1372115 (Python Code)

Max Activating Token Index: 47

Text #18

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.2710. Min Act: -0.0000

Data Index: 1500242 (Python Code)

Max Activating Token Index: 947

Text #19

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.3495. Min Act: 0.0000

Data Index: 1498509 (Python Code)

Max Activating Token Index: 255