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

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

Neuron 2294 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3468. Min Act: -0.0000

Data Index: 844362 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1093819 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1845. Min Act: -0.0000

Data Index: 436961 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1771. Min Act: -0.0000

Data Index: 679319 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1761. Min Act: -0.0000

Data Index: 243610 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1256061 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1650. Min Act: -0.0000

Data Index: 27170 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1547. Min Act: -0.0000

Data Index: 529312 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1467. Min Act: -0.0000

Data Index: 918896 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1503. Min Act: -0.0000

Data Index: 290660 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1603. Min Act: -0.0000

Data Index: 896213 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1046890 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1479. Min Act: -0.0000

Data Index: 492863 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1486. Min Act: -0.0000

Data Index: 451287 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1422. Min Act: -0.0000

Data Index: 544296 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1135884 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1323484 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1151724 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1558. Min Act: -0.0000

Data Index: 937202 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.1567. Min Act: -0.0000

Data Index: 938704 (C4 (Web Text))

Max Activating Token Index: 188