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

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

Neuron 5793 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1537713 (Python Code)

Max Activating Token Index: 292

Text #1

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2019. Min Act: -0.0000

Data Index: 361638 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1637886 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1371196 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1605171 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1609682 (Python Code)

Max Activating Token Index: 599

Text #6

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1365281 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1410807 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1487604 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1729. Min Act: -0.0000

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1496732 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1473175 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1653. Min Act: -0.0000

Data Index: 632852 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1671. Min Act: -0.0000

Data Index: 373622 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1440676 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1372722 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1552245 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1483692 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1440638 (Python Code)

Max Activating Token Index: 3