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

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

Neuron 3722 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.4747. Min Act: -0.0000

Data Index: 183012 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.4328. Min Act: -0.0000

Data Index: 657617 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.4001. Min Act: -0.0000

Data Index: 642333 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.4240. Min Act: -0.0000

Data Index: 733496 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1138605 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.4038. Min Act: -0.0000

Data Index: 645103 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3874. Min Act: -0.0000

Data Index: 981028 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3696. Min Act: -0.0000

Data Index: 659290 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3888. Min Act: -0.0000

Data Index: 225350 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1185644 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3586. Min Act: -0.0000

Data Index: 628794 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3665. Min Act: -0.0000

Data Index: 797131 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3643. Min Act: -0.0000

Data Index: 491843 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3618. Min Act: -0.0000

Data Index: 864234 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3566. Min Act: -0.0000

Data Index: 747031 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3453. Min Act: -0.0000

Data Index: 766823 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3551. Min Act: -0.0000

Data Index: 298910 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3641. Min Act: -0.0000

Data Index: 88407 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1274055 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3525. Min Act: -0.0000

Data Index: 276655 (C4 (Web Text))

Max Activating Token Index: 1018