Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5780 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0001

Data Index: 702296 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0844. Min Act: -0.0001

Data Index: 715421 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0861. Min Act: -0.0001

Data Index: 253986 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0911. Min Act: -0.0001

Data Index: 684494 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0820. Min Act: -0.0001

Data Index: 801401 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0829. Min Act: -0.0001

Data Index: 555858 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0821. Min Act: -0.0001

Data Index: 332614 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0883. Min Act: -0.0001

Data Index: 524161 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1306596 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1290824 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0802. Min Act: -0.0001

Data Index: 985084 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1611 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0755. Min Act: -0.0001

Data Index: 417562 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0730. Min Act: -0.0001

Data Index: 258210 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0717. Min Act: -0.0001

Data Index: 178237 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1185125 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0825. Min Act: -0.0001

Data Index: 667035 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0666. Min Act: -0.0001

Data Index: 700476 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1221937 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0750. Min Act: -0.0001

Data Index: 223210 (C4 (Web Text))

Max Activating Token Index: 206