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

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

Neuron 1092 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: 0.2338. Min Range: -0.2338

Max Act: 0.2338. Min Act: -0.0003

Data Index: 101364 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2177. Min Act: -0.0003

Data Index: 381193 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2056. Min Act: -0.0004

Data Index: 799704 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1970. Min Act: -0.0003

Data Index: 486075 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1945. Min Act: -0.0003

Data Index: 389589 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1830. Min Act: -0.0003

Data Index: 755830 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1723. Min Act: -0.0003

Data Index: 1038291 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1824. Min Act: -0.0003

Data Index: 940503 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1755. Min Act: -0.0004

Data Index: 485586 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1730. Min Act: -0.0003

Data Index: 160269 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1661. Min Act: -0.0003

Data Index: 566530 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1558. Min Act: -0.0002

Data Index: 46641 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1679. Min Act: -0.0003

Data Index: 1139882 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1611. Min Act: -0.0003

Data Index: 47265 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1658. Min Act: -0.0003

Data Index: 453726 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1632. Min Act: -0.0004

Data Index: 1077147 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1613. Min Act: -0.0003

Data Index: 370401 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1571. Min Act: -0.0003

Data Index: 33911 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1543. Min Act: -0.0004

Data Index: 254904 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1610. Min Act: -0.0003

Data Index: 1212192 (C4 (Web Text))

Max Activating Token Index: 768