Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1490 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0002

Data Index: 728949 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0758. Min Act: -0.0002

Data Index: 89106 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0669. Min Act: -0.0002

Data Index: 105330 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1218002 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0603. Min Act: -0.0002

Data Index: 676441 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1123395 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0562. Min Act: -0.0002

Data Index: 653544 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0571. Min Act: -0.0002

Data Index: 717547 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0533. Min Act: -0.0002

Data Index: 710154 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0553. Min Act: -0.0002

Data Index: 284028 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0548. Min Act: -0.0002

Data Index: 609450 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0509. Min Act: -0.0002

Data Index: 155993 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0505. Min Act: -0.0002

Data Index: 53677 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0501. Min Act: -0.0002

Data Index: 483199 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0498. Min Act: -0.0002

Data Index: 208044 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0471. Min Act: -0.0002

Data Index: 683108 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0516. Min Act: -0.0002

Data Index: 254291 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0526. Min Act: -0.0002

Data Index: 98965 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0516. Min Act: -0.0002

Data Index: 70723 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1031337 (C4 (Web Text))

Max Activating Token Index: 165