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

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

Neuron 1089 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: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0001

Data Index: 971563 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0962. Min Act: -0.0001

Data Index: 770231 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0860. Min Act: -0.0002

Data Index: 512446 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0896. Min Act: -0.0002

Data Index: 328735 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1351208 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0859. Min Act: -0.0002

Data Index: 637510 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0836. Min Act: -0.0002

Data Index: 573775 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0843. Min Act: -0.0002

Data Index: 904750 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0818. Min Act: 0.0000

Data Index: 1016116 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0818. Min Act: -0.0000

Data Index: 492686 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0816. Min Act: -0.0002

Data Index: 895179 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0801. Min Act: -0.0002

Data Index: 940218 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0803. Min Act: -0.0002

Data Index: 517314 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1075677 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0771. Min Act: -0.0002

Data Index: 70106 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0774. Min Act: -0.0001

Data Index: 367066 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0745. Min Act: -0.0002

Data Index: 973756 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0757. Min Act: -0.0001

Data Index: 825922 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0767. Min Act: -0.0002

Data Index: 860036 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0746. Min Act: -0.0001

Data Index: 765404 (C4 (Web Text))

Max Activating Token Index: 16