Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 114 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1575178 (Python Code)

Max Activating Token Index: 207

Text #1

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1400683 (Python Code)

Max Activating Token Index: 746

Text #2

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1473077 (Python Code)

Max Activating Token Index: 855

Text #3

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1438974 (Python Code)

Max Activating Token Index: 353

Text #4

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1537864 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1418058 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1530061 (Python Code)

Max Activating Token Index: 822

Text #7

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1442963 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1604935 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1638053 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1630813 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1527416 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1432032 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1616216 (Python Code)

Max Activating Token Index: 980

Text #14

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1484695 (Python Code)

Max Activating Token Index: 416

Text #15

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1448302 (Python Code)

Max Activating Token Index: 863

Text #16

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1462100 (Python Code)

Max Activating Token Index: 412

Text #17

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1399000 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1468140 (Python Code)

Max Activating Token Index: 306

Text #19

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1639697 (Python Code)

Max Activating Token Index: 514