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

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

Neuron 3323 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.6521. Min Act: -0.0000

Data Index: 898400 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.5727. Min Act: -0.0000

Data Index: 925011 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3802. Min Act: -0.0000

Data Index: 360246 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2706. Min Act: -0.0000

Data Index: 117559 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1375. Min Act: -0.0000

Data Index: 275899 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.9577. Min Act: -0.0000

Data Index: 255793 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1014. Min Act: -0.0000

Data Index: 425862 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1140733 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.8858. Min Act: -0.0000

Data Index: 839865 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1043280 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.8040. Min Act: -0.0000

Data Index: 766219 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7948. Min Act: -0.0000

Data Index: 404643 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7644. Min Act: -0.0000

Data Index: 707720 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1013773 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7978. Min Act: -0.0000

Data Index: 343568 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7493. Min Act: -0.0000

Data Index: 106681 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1022314 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7272. Min Act: -0.0000

Data Index: 129548 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6768. Min Act: -0.0000

Data Index: 129145 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7062. Min Act: -0.0000

Data Index: 579505 (C4 (Web Text))

Max Activating Token Index: 711