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

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

Neuron 2468 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: 1.2594. Min Range: -1.2594

Max Act: 1.2594. Min Act: -0.0000

Data Index: 590132 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.9211. Min Act: -0.0001

Data Index: 68678 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1216324 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8759. Min Act: -0.0000

Data Index: 275846 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8541. Min Act: -0.0000

Data Index: 143874 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.9170. Min Act: -0.0001

Data Index: 125259 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8152. Min Act: -0.0000

Data Index: 406453 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8316. Min Act: -0.0000

Data Index: 908372 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8422. Min Act: -0.0000

Data Index: 133332 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8185. Min Act: -0.0000

Data Index: 995145 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6702. Min Act: -0.0000

Data Index: 425458 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7906. Min Act: -0.0000

Data Index: 909555 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7314. Min Act: -0.0000

Data Index: 340454 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1235928 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7380. Min Act: -0.0000

Data Index: 24928 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7591. Min Act: -0.0000

Data Index: 636119 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7632. Min Act: -0.0000

Data Index: 161647 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1170181 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1244850 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6976. Min Act: -0.0000

Data Index: 820695 (C4 (Web Text))

Max Activating Token Index: 1022