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

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

Neuron 1469 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.5143. Min Act: -0.0001

Data Index: 951938 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1908. Min Act: -0.0001

Data Index: 146688 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1834. Min Act: -0.0001

Data Index: 808499 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1797. Min Act: -0.0001

Data Index: 224145 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.2454. Min Act: -0.0001

Data Index: 1126530 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.2422. Min Act: -0.0001

Data Index: 510116 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1877. Min Act: -0.0001

Data Index: 136204 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.2254. Min Act: -0.0001

Data Index: 1609085 (Python Code)

Max Activating Token Index: 484

Text #8

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.2102. Min Act: -0.0001

Data Index: 377917 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1823. Min Act: -0.0001

Data Index: 1465419 (Python Code)

Max Activating Token Index: 370

Text #10

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.8763. Min Act: -0.0001

Data Index: 239714 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1539. Min Act: -0.0001

Data Index: 706960 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0611. Min Act: -0.0001

Data Index: 1077432 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0974. Min Act: -0.0001

Data Index: 791369 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0656. Min Act: -0.0001

Data Index: 948438 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0614. Min Act: -0.0001

Data Index: 649301 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1237. Min Act: -0.0001

Data Index: 1240738 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0890. Min Act: -0.0001

Data Index: 1030239 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0817. Min Act: -0.0001

Data Index: 1512026 (Python Code)

Max Activating Token Index: 158

Text #19

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0520. Min Act: -0.0001

Data Index: 225739 (C4 (Web Text))

Max Activating Token Index: 601