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

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

Neuron 2451 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: 0.1079. Min Range: -0.1079

Max Act: 0.1000. Min Act: -0.0000

Data Index: 897594 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1225051 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0955. Min Act: -0.0000

Data Index: 422729 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0911. Min Act: -0.0000

Data Index: 474933 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0860. Min Act: -0.0000

Data Index: 789134 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0900. Min Act: -0.0000

Data Index: 305671 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1140276 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0843. Min Act: -0.0000

Data Index: 211945 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1089702 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1201258 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0783. Min Act: -0.0000

Data Index: 1077538 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0762. Min Act: -0.0000

Data Index: 320638 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0790. Min Act: -0.0000

Data Index: 405775 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0736. Min Act: -0.0000

Data Index: 389782 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0736. Min Act: -0.0000

Data Index: 305815 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1069460 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0757. Min Act: -0.0000

Data Index: 978538 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0753. Min Act: -0.0000

Data Index: 616732 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1215753 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0762. Min Act: -0.0000

Data Index: 909441 (C4 (Web Text))

Max Activating Token Index: 370