Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4482 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.4029. Min Act: -0.0001

Data Index: 1042786 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.3950. Min Act: -0.0001

Data Index: 715584 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.8226. Min Act: -0.0001

Data Index: 664102 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0139. Min Act: -0.0001

Data Index: 850797 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1723. Min Act: -0.0000

Data Index: 959938 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1681. Min Act: -0.0001

Data Index: 262790 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1887. Min Act: -0.0001

Data Index: 458338 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1678. Min Act: -0.0001

Data Index: 240725 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.7744. Min Act: -0.0001

Data Index: 1238065 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0399. Min Act: -0.0001

Data Index: 1049812 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0930. Min Act: -0.0001

Data Index: 985354 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1469. Min Act: -0.0001

Data Index: 901849 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1757. Min Act: -0.0001

Data Index: 569954 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1145. Min Act: -0.0001

Data Index: 840624 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9558. Min Act: -0.0001

Data Index: 835130 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0532. Min Act: -0.0000

Data Index: 812241 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0116. Min Act: -0.0001

Data Index: 985241 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9600. Min Act: -0.0001

Data Index: 1194580 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0582. Min Act: -0.0001

Data Index: 106990 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0534. Min Act: -0.0001

Data Index: 921165 (C4 (Web Text))

Max Activating Token Index: 159