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

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

Neuron 1307 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: 0.1039. Min Range: -0.1039

Max Act: 0.1039. Min Act: -0.0002

Data Index: 839577 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0921. Min Act: -0.0002

Data Index: 836723 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1301659 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1246194 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1268319 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0885. Min Act: -0.0002

Data Index: 493474 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1209334 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1065656 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0866. Min Act: -0.0002

Data Index: 874494 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0798. Min Act: -0.0002

Data Index: 196939 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0846. Min Act: -0.0002

Data Index: 552529 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0848. Min Act: -0.0002

Data Index: 30190 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0806. Min Act: -0.0002

Data Index: 883024 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0831. Min Act: -0.0002

Data Index: 484685 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0833. Min Act: -0.0002

Data Index: 22044 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0801. Min Act: -0.0002

Data Index: 866973 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0794. Min Act: -0.0002

Data Index: 663043 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0818. Min Act: -0.0002

Data Index: 754799 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0815. Min Act: -0.0002

Data Index: 469680 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1138586 (C4 (Web Text))

Max Activating Token Index: 608