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

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

Neuron 3301 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1272521 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0979. Min Act: -0.0001

Data Index: 435751 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0811. Min Act: -0.0001

Data Index: 312411 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0874. Min Act: -0.0001

Data Index: 856183 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0778. Min Act: -0.0001

Data Index: 172267 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0771. Min Act: -0.0000

Data Index: 512258 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0763. Min Act: -0.0001

Data Index: 977547 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0829. Min Act: -0.0001

Data Index: 395898 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0838. Min Act: -0.0001

Data Index: 195494 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0783. Min Act: -0.0001

Data Index: 984003 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0806. Min Act: -0.0000

Data Index: 686963 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1134944 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1005975 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0816. Min Act: -0.0001

Data Index: 168702 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0761. Min Act: -0.0001

Data Index: 469942 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0732. Min Act: -0.0001

Data Index: 389887 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1134133 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0719. Min Act: -0.0001

Data Index: 687789 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0741. Min Act: -0.0001

Data Index: 71529 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0736. Min Act: -0.0001

Data Index: 138768 (C4 (Web Text))

Max Activating Token Index: 437