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

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

Neuron 1397 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2281. Min Act: -0.0000

Data Index: 888586 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2222. Min Act: -0.0000

Data Index: 664026 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1197150 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2033. Min Act: -0.0000

Data Index: 963733 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1980. Min Act: -0.0000

Data Index: 60383 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2057. Min Act: -0.0000

Data Index: 647403 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2058. Min Act: -0.0000

Data Index: 720651 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1929. Min Act: -0.0000

Data Index: 531843 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1881. Min Act: -0.0000

Data Index: 573299 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1319236 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1903. Min Act: -0.0000

Data Index: 213947 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1847. Min Act: -0.0000

Data Index: 544146 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1816. Min Act: -0.0000

Data Index: 979737 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1812. Min Act: -0.0000

Data Index: 218109 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1177637 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1897. Min Act: -0.0000

Data Index: 503843 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1112269 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1804. Min Act: -0.0000

Data Index: 807500 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1281180 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1719. Min Act: 0.0000

Data Index: 1312347 (C4 (Web Text))

Max Activating Token Index: 715