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

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

Neuron 4889 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: 0.5720. Min Range: -0.5720

Max Act: 0.5720. Min Act: -0.0000

Data Index: 967497 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1333238 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5072. Min Act: -0.0000

Data Index: 982273 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5353. Min Act: -0.0000

Data Index: 290514 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4977. Min Act: -0.0000

Data Index: 943457 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5047. Min Act: -0.0000

Data Index: 814879 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4453. Min Act: -0.0000

Data Index: 812685 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4719. Min Act: -0.0000

Data Index: 775254 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4869. Min Act: -0.0000

Data Index: 452193 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4687. Min Act: -0.0000

Data Index: 904598 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4684. Min Act: -0.0000

Data Index: 400286 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4345. Min Act: -0.0001

Data Index: 384893 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4370. Min Act: -0.0000

Data Index: 889579 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4288. Min Act: -0.0000

Data Index: 446144 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4342. Min Act: -0.0000

Data Index: 280110 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4287. Min Act: -0.0000

Data Index: 300817 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1268314 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4568. Min Act: -0.0000

Data Index: 637835 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4562. Min Act: -0.0000

Data Index: 365804 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4123. Min Act: -0.0000

Data Index: 617874 (C4 (Web Text))

Max Activating Token Index: 554