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

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

Neuron 3815 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: 0.0911. Min Range: -0.0911

Max Act: 0.0884. Min Act: -0.0002

Data Index: 4974 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0911. Min Act: -0.0001

Data Index: 715644 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1171607 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1077868 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0699. Min Act: -0.0001

Data Index: 516673 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0708. Min Act: -0.0001

Data Index: 657680 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0738. Min Act: -0.0002

Data Index: 314997 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0703. Min Act: -0.0002

Data Index: 48383 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0638. Min Act: -0.0002

Data Index: 643265 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0684. Min Act: -0.0001

Data Index: 977022 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0651. Min Act: -0.0002

Data Index: 744800 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0670. Min Act: -0.0001

Data Index: 84675 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0695. Min Act: -0.0001

Data Index: 78863 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1082321 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0643. Min Act: -0.0001

Data Index: 265576 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0587. Min Act: -0.0001

Data Index: 799016 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0632. Min Act: -0.0002

Data Index: 718052 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0607. Min Act: -0.0002

Data Index: 91161 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0625. Min Act: -0.0002

Data Index: 572936 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0614. Min Act: -0.0002

Data Index: 636380 (C4 (Web Text))

Max Activating Token Index: 214