Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2305 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0919. Min Act: -0.0001

Data Index: 492475 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0911. Min Act: -0.0001

Data Index: 946633 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1518806 (Python Code)

Max Activating Token Index: 540

Text #3

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1169312 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0841. Min Act: -0.0002

Data Index: 546528 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0839. Min Act: -0.0001

Data Index: 724544 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1610857 (Python Code)

Max Activating Token Index: 737

Text #7

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1177121 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0758. Min Act: -0.0002

Data Index: 88590 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0804. Min Act: -0.0001

Data Index: 61879 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0760. Min Act: -0.0002

Data Index: 607724 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0726. Min Act: -0.0002

Data Index: 207195 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0763. Min Act: -0.0001

Data Index: 722280 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0732. Min Act: -0.0002

Data Index: 990005 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0645. Min Act: -0.0001

Data Index: 443179 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1289712 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0728. Min Act: -0.0001

Data Index: 648513 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1480750 (Python Code)

Max Activating Token Index: 946

Text #18

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0726. Min Act: -0.0002

Data Index: 831637 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1360870 (Python Code)

Max Activating Token Index: 39