Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 519 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0983. Min Act: -0.0001

Data Index: 675176 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0957. Min Act: -0.0001

Data Index: 977761 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0917. Min Act: -0.0001

Data Index: 286763 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1100766 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0911. Min Act: -0.0001

Data Index: 142694 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0837. Min Act: -0.0001

Data Index: 537477 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0857. Min Act: -0.0001

Data Index: 496034 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0834. Min Act: -0.0001

Data Index: 481304 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0813. Min Act: -0.0001

Data Index: 138375 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0836. Min Act: -0.0001

Data Index: 833647 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0845. Min Act: -0.0001

Data Index: 653578 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0807. Min Act: -0.0001

Data Index: 234281 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1046066 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0859. Min Act: -0.0000

Data Index: 828391 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0799. Min Act: -0.0001

Data Index: 50494 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0827. Min Act: -0.0001

Data Index: 538037 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0819. Min Act: -0.0001

Data Index: 859489 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0824. Min Act: -0.0001

Data Index: 945020 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0785. Min Act: -0.0001

Data Index: 78982 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1148021 (C4 (Web Text))

Max Activating Token Index: 555