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

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

Neuron 3733 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: 0.1028. Min Range: -0.1028

Max Act: 0.1028. Min Act: -0.0000

Data Index: 979736 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0961. Min Act: -0.0000

Data Index: 503456 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0899. Min Act: -0.0001

Data Index: 97570 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0905. Min Act: -0.0000

Data Index: 810679 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0861. Min Act: -0.0001

Data Index: 87152 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0818. Min Act: -0.0000

Data Index: 21335 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1349300 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0803. Min Act: -0.0001

Data Index: 994225 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0816. Min Act: -0.0000

Data Index: 354584 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0787. Min Act: -0.0000

Data Index: 558282 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0784. Min Act: -0.0001

Data Index: 137054 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1243322 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0790. Min Act: -0.0001

Data Index: 13513 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0784. Min Act: -0.0000

Data Index: 837864 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0789. Min Act: -0.0000

Data Index: 874705 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0731. Min Act: -0.0001

Data Index: 941824 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0756. Min Act: -0.0001

Data Index: 490233 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0744. Min Act: -0.0001

Data Index: 123615 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1198356 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1291514 (C4 (Web Text))

Max Activating Token Index: 698