Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1869 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2437. Min Act: -0.0006

Data Index: 404242 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2367. Min Act: -0.0006

Data Index: 946876 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2167. Min Act: -0.0006

Data Index: 269792 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1970. Min Act: -0.0006

Data Index: 1175367 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2037. Min Act: -0.0006

Data Index: 1346079 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1997. Min Act: -0.0006

Data Index: 742083 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2068. Min Act: -0.0006

Data Index: 753247 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1828. Min Act: -0.0006

Data Index: 478679 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1764. Min Act: -0.0006

Data Index: 872049 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1960. Min Act: -0.0006

Data Index: 809545 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1843. Min Act: -0.0006

Data Index: 909862 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1847. Min Act: -0.0006

Data Index: 1311372 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1843. Min Act: -0.0006

Data Index: 783062 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1770. Min Act: -0.0006

Data Index: 1024263 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1807. Min Act: -0.0006

Data Index: 1236743 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1724. Min Act: -0.0006

Data Index: 281168 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1778. Min Act: -0.0006

Data Index: 124052 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1846. Min Act: -0.0006

Data Index: 741830 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1796. Min Act: -0.0006

Data Index: 810347 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1830. Min Act: -0.0006

Data Index: 1079152 (C4 (Web Text))

Max Activating Token Index: 471