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

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

Neuron 2814 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0812. Min Act: -0.0001

Data Index: 31083 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0001

Data Index: 552917 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0842. Min Act: -0.0001

Data Index: 689132 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0713. Min Act: -0.0001

Data Index: 487156 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0795. Min Act: -0.0001

Data Index: 336482 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0717. Min Act: -0.0001

Data Index: 987774 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1194158 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0691. Min Act: -0.0001

Data Index: 890616 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0745. Min Act: -0.0001

Data Index: 674084 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0680. Min Act: -0.0001

Data Index: 51040 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0707. Min Act: -0.0001

Data Index: 468083 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0602. Min Act: -0.0001

Data Index: 826823 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0647. Min Act: -0.0001

Data Index: 129636 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1032094 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1094814 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0662. Min Act: -0.0001

Data Index: 859598 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0638. Min Act: -0.0001

Data Index: 438892 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0631. Min Act: -0.0001

Data Index: 498054 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0657. Min Act: -0.0001

Data Index: 448887 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0664. Min Act: -0.0001

Data Index: 699836 (C4 (Web Text))

Max Activating Token Index: 29