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

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

Neuron 293 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.3914. Min Act: -0.0001

Data Index: 174621 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.3114. Min Act: -0.0001

Data Index: 121271 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.2488. Min Act: -0.0000

Data Index: 1418332 (Python Code)

Max Activating Token Index: 821

Text #3

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.2840. Min Act: -0.0001

Data Index: 831154 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.0499. Min Act: -0.0001

Data Index: 542844 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.1254. Min Act: -0.0001

Data Index: 349132 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.1775. Min Act: -0.0001

Data Index: 178702 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.2375. Min Act: -0.0001

Data Index: 654280 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 1.3914. Min Range: -1.3914

Max Act: 0.8541. Min Act: -0.0001

Data Index: 974673 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.0595. Min Act: -0.0001

Data Index: 751662 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.3914. Min Range: -1.3914

Max Act: 0.9313. Min Act: -0.0001

Data Index: 725144 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.0293. Min Act: -0.0001

Data Index: 4695 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.0273. Min Act: -0.0001

Data Index: 548035 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 1.3914. Min Range: -1.3914

Max Act: 1.0815. Min Act: -0.0001

Data Index: 1091522 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 1.3914. Min Range: -1.3914

Max Act: 0.9329. Min Act: -0.0001

Data Index: 1059848 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 1.3914. Min Range: -1.3914

Max Act: 0.9648. Min Act: -0.0001

Data Index: 988025 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 1.3914. Min Range: -1.3914

Max Act: 0.9719. Min Act: -0.0001

Data Index: 851211 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.3914. Min Range: -1.3914

Max Act: 0.9412. Min Act: -0.0001

Data Index: 657944 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 1.3914. Min Range: -1.3914

Max Act: 0.9593. Min Act: -0.0001

Data Index: 450186 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.3914. Min Range: -1.3914

Max Act: 0.8947. Min Act: -0.0001

Data Index: 1031277 (C4 (Web Text))

Max Activating Token Index: 889