Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3426 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6749. Min Range: -1.6749

Max Act: 1.6749. Min Act: -0.0000

Data Index: 826920 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.6749. Min Range: -1.6749

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1280421 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 1.6749. Min Range: -1.6749

Max Act: 1.1985. Min Act: -0.0000

Data Index: 78672 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 1.6749. Min Range: -1.6749

Max Act: 1.0191. Min Act: -0.0000

Data Index: 408625 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1098799 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8802. Min Act: -0.0000

Data Index: 560368 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8756. Min Act: -0.0000

Data Index: 228518 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8645. Min Act: -0.0000

Data Index: 155153 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8880. Min Act: -0.0000

Data Index: 770734 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1127186 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8684. Min Act: -0.0000

Data Index: 807073 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8266. Min Act: -0.0000

Data Index: 963475 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8232. Min Act: -0.0000

Data Index: 51494 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8009. Min Act: -0.0000

Data Index: 618296 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8128. Min Act: -0.0000

Data Index: 293285 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.7917. Min Act: -0.0000

Data Index: 477347 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.7876. Min Act: -0.0000

Data Index: 885545 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8060. Min Act: -0.0000

Data Index: 828219 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.7999. Min Act: -0.0000

Data Index: 11440 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.6749. Min Range: -1.6749

Max Act: 0.8013. Min Act: -0.0000

Data Index: 147830 (C4 (Web Text))

Max Activating Token Index: 1014