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

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

Neuron 3008 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: 0.0641. Min Range: -0.0641

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1175653 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0001

Data Index: 163006 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0616. Min Act: -0.0001

Data Index: 953505 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0607. Min Act: -0.0002

Data Index: 814181 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0610. Min Act: -0.0001

Data Index: 921841 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1030812 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0558. Min Act: -0.0001

Data Index: 500976 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1245492 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0600. Min Act: -0.0001

Data Index: 574013 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1296903 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0614. Min Act: -0.0002

Data Index: 231074 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1271819 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0592. Min Act: -0.0002

Data Index: 639675 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0562. Min Act: -0.0001

Data Index: 738015 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1036509 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0584. Min Act: -0.0001

Data Index: 732874 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0557. Min Act: -0.0002

Data Index: 5638 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0522. Min Act: -0.0002

Data Index: 36731 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0512. Min Act: -0.0001

Data Index: 251267 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1094306 (C4 (Web Text))

Max Activating Token Index: 332