Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1472 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1350169 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0804. Min Act: -0.0002

Data Index: 238858 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0801. Min Act: -0.0002

Data Index: 262983 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0793. Min Act: -0.0002

Data Index: 734232 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0792. Min Act: -0.0002

Data Index: 198108 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0734. Min Act: -0.0002

Data Index: 157154 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0737. Min Act: -0.0002

Data Index: 225634 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0689. Min Act: -0.0002

Data Index: 24296 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1261411 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0681. Min Act: -0.0002

Data Index: 718924 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1199689 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0688. Min Act: -0.0002

Data Index: 907306 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0708. Min Act: -0.0002

Data Index: 543435 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0644. Min Act: -0.0002

Data Index: 920396 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0651. Min Act: -0.0002

Data Index: 389914 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0659. Min Act: -0.0002

Data Index: 823918 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0644. Min Act: -0.0002

Data Index: 751972 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0663. Min Act: -0.0002

Data Index: 178874 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0674. Min Act: -0.0002

Data Index: 977212 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0638. Min Act: -0.0002

Data Index: 122137 (C4 (Web Text))

Max Activating Token Index: 145