Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1966 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.1032. Min Act: -0.0001

Data Index: 326334 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0973. Min Act: -0.0001

Data Index: 906310 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0919. Min Act: -0.0001

Data Index: 443424 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0882. Min Act: -0.0001

Data Index: 755490 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0809. Min Act: -0.0001

Data Index: 985900 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0808. Min Act: -0.0001

Data Index: 20999 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0804. Min Act: -0.0001

Data Index: 139605 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1022889 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0787. Min Act: -0.0001

Data Index: 410534 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1357414 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0757. Min Act: -0.0001

Data Index: 774466 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0771. Min Act: -0.0001

Data Index: 550579 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0775. Min Act: -0.0001

Data Index: 397833 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0765. Min Act: -0.0001

Data Index: 863876 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0821. Min Act: -0.0001

Data Index: 259266 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0767. Min Act: -0.0001

Data Index: 45477 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0791. Min Act: -0.0001

Data Index: 417144 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0793. Min Act: -0.0001

Data Index: 85249 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1228660 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0824. Min Act: -0.0001

Data Index: 228398 (C4 (Web Text))

Max Activating Token Index: 618