Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 140 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2116. Min Range: -1.2116

Max Act: 1.2116. Min Act: -0.0003

Data Index: 832542 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.2116. Min Range: -1.2116

Max Act: 1.1372. Min Act: -0.0003

Data Index: 288196 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.2116. Min Range: -1.2116

Max Act: 1.0792. Min Act: -0.0003

Data Index: 1170785 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 1.2116. Min Range: -1.2116

Max Act: 1.0816. Min Act: -0.0003

Data Index: 40341 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.2116. Min Range: -1.2116

Max Act: 1.0785. Min Act: -0.0003

Data Index: 1608774 (Python Code)

Max Activating Token Index: 858

Text #5

Max Range: 1.2116. Min Range: -1.2116

Max Act: 1.0329. Min Act: -0.0003

Data Index: 1479088 (Python Code)

Max Activating Token Index: 825

Text #6

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9656. Min Act: -0.0003

Data Index: 133084 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9772. Min Act: -0.0003

Data Index: 1385878 (Python Code)

Max Activating Token Index: 931

Text #8

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9723. Min Act: -0.0003

Data Index: 677687 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9446. Min Act: -0.0003

Data Index: 1550311 (Python Code)

Max Activating Token Index: 486

Text #10

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.8556. Min Act: -0.0003

Data Index: 1417699 (Python Code)

Max Activating Token Index: 803

Text #11

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9121. Min Act: -0.0003

Data Index: 1561143 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9980. Min Act: -0.0003

Data Index: 296405 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9308. Min Act: -0.0003

Data Index: 360956 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9231. Min Act: -0.0003

Data Index: 1597547 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9488. Min Act: -0.0003

Data Index: 413796 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9555. Min Act: -0.0003

Data Index: 1525472 (Python Code)

Max Activating Token Index: 945

Text #17

Max Range: 1.2116. Min Range: -1.2116

Max Act: 1.0091. Min Act: -0.0003

Data Index: 1267925 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9564. Min Act: -0.0003

Data Index: 886506 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9181. Min Act: -0.0003

Data Index: 1578208 (Python Code)

Max Activating Token Index: 396