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

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

Neuron 3865 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: 1.0788. Min Range: -1.0788

Max Act: 1.0559. Min Act: -0.0001

Data Index: 777832 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 1.0788. Min Range: -1.0788

Max Act: 1.0788. Min Act: -0.0001

Data Index: 728114 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 1.0788. Min Range: -1.0788

Max Act: 1.0689. Min Act: -0.0001

Data Index: 387432 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 1.0788. Min Range: -1.0788

Max Act: 1.0277. Min Act: -0.0001

Data Index: 1122067 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9787. Min Act: -0.0001

Data Index: 793096 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9721. Min Act: -0.0001

Data Index: 43596 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9666. Min Act: -0.0001

Data Index: 1175578 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9334. Min Act: -0.0001

Data Index: 1293607 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8782. Min Act: -0.0001

Data Index: 369524 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9762. Min Act: -0.0001

Data Index: 70800 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9439. Min Act: -0.0001

Data Index: 937977 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9733. Min Act: -0.0001

Data Index: 1303411 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9436. Min Act: -0.0001

Data Index: 212960 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9625. Min Act: -0.0001

Data Index: 1339330 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9291. Min Act: -0.0001

Data Index: 80321 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9290. Min Act: -0.0001

Data Index: 221371 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9140. Min Act: -0.0001

Data Index: 570853 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8802. Min Act: -0.0001

Data Index: 950565 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9297. Min Act: -0.0001

Data Index: 1018047 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9047. Min Act: -0.0001

Data Index: 742818 (C4 (Web Text))

Max Activating Token Index: 285