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

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

Neuron 3173 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4990. Min Act: -0.0002

Data Index: 1027495 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4015. Min Act: -0.0002

Data Index: 209272 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4292. Min Act: -0.0002

Data Index: 381949 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3823. Min Act: -0.0002

Data Index: 758241 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4194. Min Act: -0.0002

Data Index: 196549 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4482. Min Act: -0.0002

Data Index: 405016 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4109. Min Act: -0.0002

Data Index: 778390 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3738. Min Act: -0.0002

Data Index: 168123 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4429. Min Act: -0.0002

Data Index: 866978 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3942. Min Act: -0.0002

Data Index: 721889 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4021. Min Act: -0.0002

Data Index: 1069908 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4332. Min Act: -0.0002

Data Index: 818511 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4003. Min Act: -0.0002

Data Index: 1220863 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4538. Min Act: -0.0002

Data Index: 1135873 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3718. Min Act: -0.0002

Data Index: 1034088 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4083. Min Act: -0.0002

Data Index: 1086987 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3926. Min Act: -0.0002

Data Index: 1147266 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3805. Min Act: -0.0002

Data Index: 721472 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3340. Min Act: -0.0002

Data Index: 172110 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3245. Min Act: -0.0002

Data Index: 1216761 (C4 (Web Text))

Max Activating Token Index: 888