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

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

Neuron 1491 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2201. Min Act: -0.0003

Data Index: 53214 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1962. Min Act: -0.0003

Data Index: 701799 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1847. Min Act: -0.0003

Data Index: 956857 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1987. Min Act: -0.0004

Data Index: 1175484 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1935. Min Act: -0.0003

Data Index: 42245 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1832. Min Act: -0.0003

Data Index: 339372 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1853. Min Act: -0.0003

Data Index: 756163 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1819. Min Act: -0.0004

Data Index: 290107 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1760. Min Act: -0.0003

Data Index: 254120 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1692. Min Act: -0.0004

Data Index: 385377 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1734. Min Act: -0.0003

Data Index: 379238 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1677. Min Act: -0.0003

Data Index: 1018452 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1770. Min Act: -0.0003

Data Index: 916059 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1658. Min Act: -0.0003

Data Index: 532459 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1770. Min Act: -0.0003

Data Index: 939740 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1659. Min Act: -0.0003

Data Index: 358401 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1698. Min Act: -0.0003

Data Index: 1340423 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1752. Min Act: -0.0003

Data Index: 255351 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1591. Min Act: -0.0004

Data Index: 1227585 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1676. Min Act: -0.0003

Data Index: 625066 (C4 (Web Text))

Max Activating Token Index: 309