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

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

Neuron 4460 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: 0.2245. Min Range: -0.2245

Max Act: 0.2245. Min Act: -0.0000

Data Index: 349006 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.2013. Min Act: -0.0000

Data Index: 403900 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1315599 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1934. Min Act: -0.0000

Data Index: 853966 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1707. Min Act: -0.0000

Data Index: 993331 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1148046 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1573. Min Act: -0.0000

Data Index: 569371 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1339457 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1605. Min Act: -0.0000

Data Index: 876179 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1598. Min Act: -0.0000

Data Index: 798978 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1551. Min Act: -0.0000

Data Index: 147781 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1552. Min Act: -0.0000

Data Index: 995254 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1417. Min Act: -0.0000

Data Index: 85503 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1395. Min Act: -0.0000

Data Index: 384159 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1402. Min Act: -0.0000

Data Index: 368892 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1288520 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1395. Min Act: -0.0000

Data Index: 837824 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1332620 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1546. Min Act: -0.0000

Data Index: 485753 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1422. Min Act: -0.0000

Data Index: 70674 (C4 (Web Text))

Max Activating Token Index: 651