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

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

Neuron 1809 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0001

Data Index: 373314 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1047830 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0926. Min Act: -0.0001

Data Index: 216603 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0931. Min Act: -0.0001

Data Index: 52797 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0895. Min Act: -0.0001

Data Index: 254323 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0895. Min Act: -0.0001

Data Index: 421990 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0895. Min Act: -0.0001

Data Index: 795263 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0808. Min Act: -0.0001

Data Index: 912465 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0901. Min Act: -0.0001

Data Index: 546847 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0906. Min Act: -0.0001

Data Index: 830683 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0860. Min Act: -0.0001

Data Index: 821714 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0861. Min Act: -0.0001

Data Index: 245339 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0878. Min Act: -0.0001

Data Index: 45233 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1106594 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1234041 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0779. Min Act: -0.0001

Data Index: 692499 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1232982 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0759. Min Act: -0.0001

Data Index: 740221 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0804. Min Act: -0.0001

Data Index: 749004 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1001086 (C4 (Web Text))

Max Activating Token Index: 339