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

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

Neuron 698 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1152. Min Act: -0.0000

Data Index: 556048 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0984. Min Act: -0.0000

Data Index: 490930 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1062360 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0864. Min Act: -0.0001

Data Index: 939628 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1165274 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0672. Min Act: -0.0001

Data Index: 739127 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0782. Min Act: -0.0001

Data Index: 377311 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1027390 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0734. Min Act: -0.0000

Data Index: 679416 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0801. Min Act: 0.0000

Data Index: 1003466 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0740. Min Act: -0.0000

Data Index: 948050 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0670. Min Act: -0.0000

Data Index: 360070 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0734. Min Act: 0.0000

Data Index: 145153 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0674. Min Act: -0.0000

Data Index: 535946 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0598. Min Act: -0.0000

Data Index: 628339 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0630. Min Act: -0.0001

Data Index: 245276 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0648. Min Act: 0.0001

Data Index: 1279278 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0654. Min Act: 0.0001

Data Index: 937021 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0640. Min Act: -0.0001

Data Index: 733954 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0662. Min Act: -0.0000

Data Index: 703054 (C4 (Web Text))

Max Activating Token Index: 42