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

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

Neuron 1020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1812. Min Act: -0.0000

Data Index: 467971 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1248954 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1176. Min Act: -0.0000

Data Index: 414538 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1195. Min Act: -0.0000

Data Index: 854837 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1060. Min Act: -0.0000

Data Index: 364181 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1162. Min Act: -0.0000

Data Index: 120126 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1126. Min Act: -0.0000

Data Index: 654119 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1064. Min Act: -0.0000

Data Index: 872018 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1017. Min Act: -0.0000

Data Index: 512355 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1104289 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.0993. Min Act: -0.0000

Data Index: 804281 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1002. Min Act: -0.0000

Data Index: 948694 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1180308 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1004. Min Act: -0.0000

Data Index: 949418 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.0968. Min Act: -0.0000

Data Index: 971864 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.0962. Min Act: -0.0000

Data Index: 846766 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1025. Min Act: -0.0000

Data Index: 667458 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1027. Min Act: -0.0000

Data Index: 354073 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.0889. Min Act: -0.0000

Data Index: 328829 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.0887. Min Act: -0.0000

Data Index: 74362 (C4 (Web Text))

Max Activating Token Index: 925