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

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

Neuron 4576 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2733. Min Range: -1.2733

Max Act: 1.2733. Min Act: -0.0000

Data Index: 927040 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.2733. Min Range: -1.2733

Max Act: 1.1274. Min Act: -0.0001

Data Index: 974891 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.2733. Min Range: -1.2733

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1045594 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 1.2733. Min Range: -1.2733

Max Act: 1.0935. Min Act: -0.0000

Data Index: 1352834 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9473. Min Act: -0.0000

Data Index: 669005 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9446. Min Act: -0.0001

Data Index: 1110019 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 1.2733. Min Range: -1.2733

Max Act: 1.0680. Min Act: -0.0001

Data Index: 162251 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9740. Min Act: -0.0001

Data Index: 801487 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9676. Min Act: -0.0001

Data Index: 765967 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.2733. Min Range: -1.2733

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1268901 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9017. Min Act: -0.0001

Data Index: 146787 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9006. Min Act: -0.0000

Data Index: 172413 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9405. Min Act: -0.0001

Data Index: 458354 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1267861 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9029. Min Act: -0.0000

Data Index: 427306 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9042. Min Act: -0.0001

Data Index: 1184933 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.8730. Min Act: -0.0000

Data Index: 788336 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.8707. Min Act: -0.0001

Data Index: 262775 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9923. Min Act: -0.0001

Data Index: 646320 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.2733. Min Range: -1.2733

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1161367 (C4 (Web Text))

Max Activating Token Index: 574