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

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

Neuron 2246 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0969. Min Act: -0.0001

Data Index: 795752 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0850. Min Act: -0.0001

Data Index: 994620 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0817. Min Act: -0.0001

Data Index: 507777 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0818. Min Act: -0.0002

Data Index: 695543 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0836. Min Act: -0.0002

Data Index: 488686 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1241421 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0790. Min Act: -0.0002

Data Index: 972899 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0769. Min Act: -0.0002

Data Index: 757199 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0792. Min Act: -0.0001

Data Index: 836856 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1206665 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0782. Min Act: -0.0001

Data Index: 264096 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0780. Min Act: -0.0002

Data Index: 945649 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1116901 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0771. Min Act: -0.0001

Data Index: 560770 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1005793 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0733. Min Act: -0.0002

Data Index: 990220 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1194942 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0766. Min Act: -0.0002

Data Index: 285752 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0784. Min Act: -0.0001

Data Index: 663307 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0748. Min Act: -0.0001

Data Index: 517756 (C4 (Web Text))

Max Activating Token Index: 993