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

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

Neuron 168 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: 1.1412. Min Range: -1.1412

Max Act: 1.1412. Min Act: -0.0001

Data Index: 1180794 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0770. Min Act: -0.0001

Data Index: 774812 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0146. Min Act: -0.0001

Data Index: 923312 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0164. Min Act: -0.0001

Data Index: 1025596 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.8973. Min Act: -0.0001

Data Index: 220035 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9128. Min Act: -0.0001

Data Index: 104408 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.8458. Min Act: -0.0001

Data Index: 798451 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9014. Min Act: -0.0001

Data Index: 60488 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9131. Min Act: -0.0001

Data Index: 603281 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7913. Min Act: -0.0001

Data Index: 235726 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7745. Min Act: -0.0001

Data Index: 927585 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7823. Min Act: -0.0001

Data Index: 586824 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.8899. Min Act: -0.0001

Data Index: 977995 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.8367. Min Act: -0.0001

Data Index: 666592 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7945. Min Act: -0.0001

Data Index: 942214 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7257. Min Act: -0.0001

Data Index: 91727 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7487. Min Act: -0.0001

Data Index: 813003 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7963. Min Act: -0.0001

Data Index: 271642 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7329. Min Act: -0.0001

Data Index: 333781 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7676. Min Act: -0.0001

Data Index: 791635 (C4 (Web Text))

Max Activating Token Index: 973