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

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

Neuron 1769 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1237. Min Act: -0.0000

Data Index: 329977 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1175. Min Act: -0.0000

Data Index: 902004 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1013. Min Act: -0.0000

Data Index: 874097 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0964. Min Act: -0.0000

Data Index: 892590 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0968. Min Act: -0.0000

Data Index: 885176 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1181556 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0847. Min Act: -0.0000

Data Index: 849229 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0931. Min Act: -0.0000

Data Index: 798208 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0874. Min Act: -0.0000

Data Index: 208845 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1146711 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0880. Min Act: -0.0000

Data Index: 204390 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0874. Min Act: -0.0000

Data Index: 866626 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1120558 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0889. Min Act: -0.0000

Data Index: 785117 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0885. Min Act: -0.0000

Data Index: 877330 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0807. Min Act: -0.0000

Data Index: 78070 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0798. Min Act: -0.0000

Data Index: 672982 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0765. Min Act: -0.0000

Data Index: 321267 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0826. Min Act: -0.0000

Data Index: 559771 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0864. Min Act: -0.0000

Data Index: 553149 (C4 (Web Text))

Max Activating Token Index: 588