Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1161 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0746. Min Act: -0.0003

Data Index: 318039 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0004

Data Index: 1296198 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0675. Min Act: -0.0004

Data Index: 938644 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1234490 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1056236 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0650. Min Act: -0.0003

Data Index: 286050 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1043475 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0612. Min Act: -0.0002

Data Index: 82861 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0647. Min Act: -0.0004

Data Index: 1045557 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0620. Min Act: -0.0004

Data Index: 385815 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0618. Min Act: -0.0003

Data Index: 324101 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0636. Min Act: -0.0003

Data Index: 322137 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0589. Min Act: -0.0003

Data Index: 855017 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1019017 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0636. Min Act: -0.0004

Data Index: 213527 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0612. Min Act: -0.0004

Data Index: 841220 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0611. Min Act: -0.0003

Data Index: 760222 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1044710 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0577. Min Act: -0.0003

Data Index: 969814 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0579. Min Act: -0.0003

Data Index: 283728 (C4 (Web Text))

Max Activating Token Index: 257