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

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

Neuron 1991 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: 0.1161. Min Range: -0.1161

Max Act: 0.1161. Min Act: -0.0002

Data Index: 730638 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1025. Min Act: -0.0002

Data Index: 905799 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1282868 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1004. Min Act: -0.0002

Data Index: 310923 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1012. Min Act: -0.0002

Data Index: 646441 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1066. Min Act: -0.0002

Data Index: 627802 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0978. Min Act: -0.0002

Data Index: 516243 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1254948 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0996. Min Act: -0.0002

Data Index: 497988 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1300242 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0966. Min Act: -0.0002

Data Index: 214344 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1350795 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0960. Min Act: -0.0002

Data Index: 894731 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0974. Min Act: -0.0002

Data Index: 45060 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1336997 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0974. Min Act: -0.0002

Data Index: 987951 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1147492 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0903. Min Act: -0.0002

Data Index: 665854 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0892. Min Act: -0.0002

Data Index: 265173 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0915. Min Act: -0.0002

Data Index: 532804 (C4 (Web Text))

Max Activating Token Index: 831