Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1307 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1240. Min Act: -0.0004

Data Index: 598410 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0840. Min Act: -0.0004

Data Index: 1321053 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0824. Min Act: -0.0004

Data Index: 504714 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0825. Min Act: -0.0004

Data Index: 28645 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0781. Min Act: -0.0004

Data Index: 697759 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0774. Min Act: -0.0004

Data Index: 619010 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0795. Min Act: -0.0004

Data Index: 1118921 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0810. Min Act: -0.0004

Data Index: 1075793 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0757. Min Act: -0.0004

Data Index: 464670 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0729. Min Act: -0.0004

Data Index: 789070 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0748. Min Act: -0.0004

Data Index: 282514 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0746. Min Act: -0.0004

Data Index: 637758 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0700. Min Act: -0.0004

Data Index: 96626 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0677. Min Act: -0.0004

Data Index: 776306 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0668. Min Act: -0.0004

Data Index: 998817 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0616. Min Act: -0.0004

Data Index: 1065360 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0677. Min Act: -0.0004

Data Index: 578057 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0676. Min Act: -0.0004

Data Index: 1169655 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0678. Min Act: -0.0004

Data Index: 1327481 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0674. Min Act: -0.0004

Data Index: 809138 (C4 (Web Text))

Max Activating Token Index: 356