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

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

Neuron 67 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.3295. Min Act: -0.0000

Data Index: 680595 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.3675. Min Act: -0.0000

Data Index: 1208114 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.2610. Min Act: -0.0000

Data Index: 997701 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.2087. Min Act: -0.0000

Data Index: 517426 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1973. Min Act: -0.0000

Data Index: 996913 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1867. Min Act: -0.0000

Data Index: 443941 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1871. Min Act: -0.0000

Data Index: 234231 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1782. Min Act: -0.0000

Data Index: 360718 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1633. Min Act: -0.0000

Data Index: 595896 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1518. Min Act: -0.0000

Data Index: 760104 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1614. Min Act: -0.0000

Data Index: 467078 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1514. Min Act: -0.0000

Data Index: 309003 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.2145. Min Act: -0.0000

Data Index: 311893 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.2007. Min Act: -0.0000

Data Index: 251257 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.0555. Min Act: -0.0000

Data Index: 146116 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.0566. Min Act: -0.0000

Data Index: 9605 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1158. Min Act: -0.0000

Data Index: 318819 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1127. Min Act: -0.0000

Data Index: 860034 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1357511 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.0948. Min Act: -0.0000

Data Index: 123551 (C4 (Web Text))

Max Activating Token Index: 248