Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 579 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1483152 (Python Code)

Max Activating Token Index: 543

Text #1

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1387178 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2125. Min Act: -0.0001

Data Index: 1540361 (Python Code)

Max Activating Token Index: 602

Text #3

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1472862 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1476862 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1499423 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1523507 (Python Code)

Max Activating Token Index: 709

Text #7

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2040. Min Act: -0.0001

Data Index: 1449723 (Python Code)

Max Activating Token Index: 449

Text #8

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1484907 (Python Code)

Max Activating Token Index: 824

Text #9

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1541992 (Python Code)

Max Activating Token Index: 642

Text #10

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1387516 (Python Code)

Max Activating Token Index: 348

Text #11

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2066. Min Act: -0.0001

Data Index: 1459137 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1513282 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1483938 (Python Code)

Max Activating Token Index: 755

Text #14

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1495506 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1533092 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1604779 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2021. Min Act: -0.0001

Data Index: 1535515 (Python Code)

Max Activating Token Index: 970

Text #18

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1494580 (Python Code)

Max Activating Token Index: 982

Text #19

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1439152 (Python Code)

Max Activating Token Index: 546