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

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

Neuron 1393 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1080797 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0934. Min Act: -0.0000

Data Index: 68052 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0933. Min Act: -0.0000

Data Index: 230118 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0982. Min Act: -0.0000

Data Index: 669116 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0843. Min Act: -0.0000

Data Index: 361645 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1072839 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0840. Min Act: -0.0000

Data Index: 765596 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0836. Min Act: -0.0000

Data Index: 426807 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0797. Min Act: -0.0000

Data Index: 275414 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0870. Min Act: -0.0000

Data Index: 658777 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0800. Min Act: -0.0000

Data Index: 167757 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0818. Min Act: -0.0000

Data Index: 834676 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1118621 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1105594 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1077231 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0771. Min Act: -0.0000

Data Index: 583443 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0769. Min Act: -0.0000

Data Index: 701412 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0794. Min Act: -0.0000

Data Index: 510821 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0768. Min Act: -0.0000

Data Index: 731165 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1263729 (C4 (Web Text))

Max Activating Token Index: 902