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

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

Neuron 340 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0715. Min Range: -2.0715

Max Act: 2.0329. Min Act: -0.0000

Data Index: 955255 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.9588. Min Act: -0.0001

Data Index: 174643 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 2.0715. Min Range: -2.0715

Max Act: 2.0272. Min Act: -0.0000

Data Index: 1083506 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.8787. Min Act: -0.0000

Data Index: 1082595 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 2.0715. Min Range: -2.0715

Max Act: 2.0715. Min Act: -0.0001

Data Index: 1405332 (Python Code)

Max Activating Token Index: 791

Text #5

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.9155. Min Act: -0.0000

Data Index: 395375 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.7143. Min Act: -0.0000

Data Index: 937190 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.6648. Min Act: -0.0000

Data Index: 1239863 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.6404. Min Act: -0.0000

Data Index: 5122 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.6224. Min Act: -0.0000

Data Index: 1224711 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.7073. Min Act: -0.0000

Data Index: 570704 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.5667. Min Act: -0.0000

Data Index: 380708 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.4764. Min Act: -0.0000

Data Index: 1111804 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.4748. Min Act: -0.0000

Data Index: 213752 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.5121. Min Act: -0.0000

Data Index: 519910 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.5556. Min Act: -0.0000

Data Index: 1228275 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.5413. Min Act: -0.0000

Data Index: 561139 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.5369. Min Act: -0.0000

Data Index: 1059258 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.5017. Min Act: -0.0001

Data Index: 818134 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 2.0715. Min Range: -2.0715

Max Act: 1.4822. Min Act: -0.0000

Data Index: 124922 (C4 (Web Text))

Max Activating Token Index: 503