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

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

Neuron 1474 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0879. Min Act: -0.0000

Data Index: 353044 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1161417 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0838. Min Act: -0.0000

Data Index: 339641 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0791. Min Act: -0.0000

Data Index: 1590 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0771. Min Act: -0.0000

Data Index: 631404 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0770. Min Act: -0.0001

Data Index: 492293 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0827. Min Act: -0.0001

Data Index: 441771 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0716. Min Act: -0.0001

Data Index: 958254 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0752. Min Act: -0.0001

Data Index: 653932 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0750. Min Act: -0.0000

Data Index: 575911 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1039076 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1351149 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0721. Min Act: -0.0001

Data Index: 204188 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0742. Min Act: -0.0000

Data Index: 783451 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0711. Min Act: -0.0000

Data Index: 485917 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0711. Min Act: -0.0000

Data Index: 169176 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0789. Min Act: -0.0000

Data Index: 668793 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0691. Min Act: -0.0001

Data Index: 412097 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0693. Min Act: -0.0001

Data Index: 684577 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1204120 (C4 (Web Text))

Max Activating Token Index: 512