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

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

Neuron 708 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5732. Min Act: -0.0000

Data Index: 647355 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5744. Min Act: -0.0000

Data Index: 204706 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5661. Min Act: -0.0000

Data Index: 597619 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5585. Min Act: -0.0000

Data Index: 704538 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5094. Min Act: -0.0000

Data Index: 969862 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5443. Min Act: -0.0000

Data Index: 774547 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1271524 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5212. Min Act: -0.0000

Data Index: 782609 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5081. Min Act: -0.0000

Data Index: 971764 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5210. Min Act: -0.0000

Data Index: 183826 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1004884 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4734. Min Act: -0.0000

Data Index: 241677 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4897. Min Act: -0.0000

Data Index: 66084 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1289825 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4834. Min Act: -0.0000

Data Index: 166657 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4905. Min Act: -0.0000

Data Index: 76846 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4711. Min Act: -0.0000

Data Index: 687777 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4890. Min Act: -0.0000

Data Index: 536000 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4596. Min Act: -0.0000

Data Index: 347786 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4849. Min Act: -0.0000

Data Index: 324530 (C4 (Web Text))

Max Activating Token Index: 735