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

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

Neuron 3312 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1720. Min Act: -0.0002

Data Index: 202859 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1783. Min Act: -0.0002

Data Index: 691220 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1773. Min Act: -0.0002

Data Index: 868325 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1751. Min Act: -0.0002

Data Index: 426233 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1740. Min Act: -0.0002

Data Index: 904935 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1736. Min Act: -0.0002

Data Index: 1355329 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1735. Min Act: -0.0002

Data Index: 1305077 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1729. Min Act: -0.0002

Data Index: 120901 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 1497198 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 1433402 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 1447898 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 1488149 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 1361934 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 549326 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 747648 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 258929 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 294344 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 364373 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 956146 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1715. Min Act: -0.0002

Data Index: 481622 (C4 (Web Text))

Max Activating Token Index: 1