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

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

Neuron 5091 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.3378. Min Act: -0.0002

Data Index: 652120 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.3353. Min Act: -0.0002

Data Index: 1111516 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.3143. Min Act: -0.0002

Data Index: 698213 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.3040. Min Act: -0.0002

Data Index: 345499 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.2864. Min Act: -0.0002

Data Index: 913024 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.3146. Min Act: -0.0002

Data Index: 1340588 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.2108. Min Act: -0.0002

Data Index: 376114 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1511. Min Act: -0.0002

Data Index: 1242947 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1598. Min Act: -0.0002

Data Index: 646720 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0894. Min Act: -0.0002

Data Index: 1036263 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1189. Min Act: -0.0002

Data Index: 559724 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1089. Min Act: -0.0002

Data Index: 1132968 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0631. Min Act: -0.0002

Data Index: 564680 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0975. Min Act: -0.0002

Data Index: 918578 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1290. Min Act: -0.0002

Data Index: 48752 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0265. Min Act: -0.0002

Data Index: 118330 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0850. Min Act: -0.0002

Data Index: 812742 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0884. Min Act: -0.0002

Data Index: 1137107 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0837. Min Act: -0.0002

Data Index: 1069772 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0197. Min Act: -0.0002

Data Index: 49418 (C4 (Web Text))

Max Activating Token Index: 9