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

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

Neuron 1459 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0949. Min Act: -0.0001

Data Index: 776200 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.1027. Min Act: -0.0001

Data Index: 696701 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0899. Min Act: -0.0000

Data Index: 179286 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0926. Min Act: -0.0000

Data Index: 188307 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1238608 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1031557 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0865. Min Act: -0.0001

Data Index: 421185 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0829. Min Act: -0.0000

Data Index: 476667 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0937. Min Act: -0.0001

Data Index: 628128 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0809. Min Act: -0.0001

Data Index: 949879 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0743. Min Act: -0.0001

Data Index: 265720 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1326664 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0723. Min Act: -0.0001

Data Index: 192448 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1026614 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0715. Min Act: -0.0001

Data Index: 834314 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0721. Min Act: -0.0000

Data Index: 601874 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1559977 (Python Code)

Max Activating Token Index: 823

Text #17

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0742. Min Act: -0.0000

Data Index: 802501 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0743. Min Act: -0.0000

Data Index: 294107 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0732. Min Act: -0.0001

Data Index: 454193 (C4 (Web Text))

Max Activating Token Index: 915