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

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

Neuron 5375 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0002

Data Index: 558628 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1001. Min Act: -0.0002

Data Index: 5235 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0965. Min Act: -0.0002

Data Index: 544983 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0936. Min Act: -0.0002

Data Index: 145360 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0851. Min Act: -0.0002

Data Index: 867214 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0838. Min Act: -0.0002

Data Index: 59454 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0825. Min Act: -0.0002

Data Index: 237752 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0820. Min Act: -0.0002

Data Index: 940611 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0834. Min Act: -0.0002

Data Index: 230554 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0832. Min Act: -0.0002

Data Index: 824925 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0801. Min Act: -0.0002

Data Index: 229929 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0808. Min Act: -0.0002

Data Index: 529066 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1019391 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1238735 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0724. Min Act: -0.0002

Data Index: 391024 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0745. Min Act: -0.0002

Data Index: 5189 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0734. Min Act: -0.0002

Data Index: 375965 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0723. Min Act: -0.0002

Data Index: 964901 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1347155 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0737. Min Act: -0.0002

Data Index: 271512 (C4 (Web Text))

Max Activating Token Index: 736