Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1956 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1354669 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0923. Min Act: -0.0003

Data Index: 610298 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0895. Min Act: -0.0003

Data Index: 598988 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0871. Min Act: -0.0003

Data Index: 1102235 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0886. Min Act: -0.0003

Data Index: 920198 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0855. Min Act: -0.0003

Data Index: 279825 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0853. Min Act: -0.0003

Data Index: 143595 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0848. Min Act: -0.0003

Data Index: 745706 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0864. Min Act: -0.0003

Data Index: 379977 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0825. Min Act: -0.0003

Data Index: 175550 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1229054 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0832. Min Act: -0.0003

Data Index: 922339 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0812. Min Act: -0.0004

Data Index: 925465 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0801. Min Act: -0.0003

Data Index: 412527 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0803. Min Act: -0.0003

Data Index: 24139 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0818. Min Act: -0.0003

Data Index: 571393 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0790. Min Act: -0.0003

Data Index: 546082 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0764. Min Act: -0.0003

Data Index: 1006509 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0758. Min Act: -0.0003

Data Index: 294880 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0812. Min Act: -0.0003

Data Index: 314952 (C4 (Web Text))

Max Activating Token Index: 513