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

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

Neuron 818 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.1392. Min Act: -0.0001

Data Index: 1406696 (Python Code)

Max Activating Token Index: 672

Text #1

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.1927. Min Act: -0.0001

Data Index: 438659 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.2035. Min Act: -0.0001

Data Index: 212563 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.1134. Min Act: -0.0001

Data Index: 1512171 (Python Code)

Max Activating Token Index: 506

Text #4

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9948. Min Act: -0.0001

Data Index: 322614 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9749. Min Act: -0.0001

Data Index: 299580 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0449. Min Act: -0.0001

Data Index: 1236897 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9763. Min Act: -0.0001

Data Index: 554500 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0322. Min Act: -0.0001

Data Index: 555756 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0500. Min Act: -0.0001

Data Index: 1482612 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9350. Min Act: -0.0001

Data Index: 1291702 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9537. Min Act: -0.0001

Data Index: 637425 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9234. Min Act: -0.0001

Data Index: 406654 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9714. Min Act: -0.0001

Data Index: 107269 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9514. Min Act: -0.0001

Data Index: 1482349 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9812. Min Act: -0.0001

Data Index: 448822 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0984. Min Act: -0.0001

Data Index: 917222 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9716. Min Act: -0.0001

Data Index: 958240 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9447. Min Act: -0.0001

Data Index: 616854 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0003. Min Act: -0.0001

Data Index: 239105 (C4 (Web Text))

Max Activating Token Index: 976