Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5169 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1335717 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3312. Min Act: -0.0000

Data Index: 237425 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3281. Min Act: -0.0000

Data Index: 450581 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1195559 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3102. Min Act: -0.0000

Data Index: 693404 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3037. Min Act: -0.0000

Data Index: 716500 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2909. Min Act: -0.0000

Data Index: 956531 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2892. Min Act: -0.0000

Data Index: 383418 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2765. Min Act: -0.0000

Data Index: 982838 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2757. Min Act: -0.0000

Data Index: 740104 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2857. Min Act: -0.0000

Data Index: 427400 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2721. Min Act: -0.0000

Data Index: 408815 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1261100 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1079387 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2773. Min Act: -0.0000

Data Index: 640520 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1237159 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2819. Min Act: -0.0000

Data Index: 904280 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2693. Min Act: -0.0000

Data Index: 163817 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1129060 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2619. Min Act: -0.0000

Data Index: 452807 (C4 (Web Text))

Max Activating Token Index: 653