Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1856 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0968. Min Act: -0.0003

Data Index: 808503 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0003

Data Index: 583659 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0955. Min Act: -0.0004

Data Index: 762815 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0936. Min Act: -0.0003

Data Index: 809616 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0933. Min Act: -0.0003

Data Index: 623480 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0879. Min Act: -0.0003

Data Index: 844417 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0922. Min Act: -0.0003

Data Index: 944966 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0886. Min Act: -0.0003

Data Index: 636156 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1179816 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1179896 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1096471 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0870. Min Act: -0.0003

Data Index: 413573 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0855. Min Act: -0.0003

Data Index: 927562 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0853. Min Act: -0.0003

Data Index: 334095 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0838. Min Act: -0.0003

Data Index: 975748 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0877. Min Act: -0.0003

Data Index: 483035 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0875. Min Act: -0.0003

Data Index: 1221768 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0869. Min Act: -0.0003

Data Index: 585215 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0863. Min Act: -0.0003

Data Index: 349815 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0843. Min Act: -0.0003

Data Index: 618571 (C4 (Web Text))

Max Activating Token Index: 539