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

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

Neuron 3116 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2908. Min Act: -0.0000

Data Index: 919258 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2815. Min Act: -0.0000

Data Index: 937410 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1199086 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1256666 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2989. Min Act: -0.0000

Data Index: 628393 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2934. Min Act: -0.0000

Data Index: 194546 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2863. Min Act: -0.0000

Data Index: 627227 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1336999 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2900. Min Act: -0.0000

Data Index: 757592 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2571. Min Act: -0.0000

Data Index: 481177 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2568. Min Act: 0.0000

Data Index: 862909 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2548. Min Act: -0.0000

Data Index: 731060 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2718. Min Act: -0.0000

Data Index: 748153 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1142744 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2569. Min Act: -0.0000

Data Index: 718041 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2389. Min Act: -0.0000

Data Index: 104026 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2532. Min Act: -0.0000

Data Index: 422546 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2533. Min Act: -0.0000

Data Index: 399752 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2530. Min Act: -0.0000

Data Index: 180726 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2590. Min Act: -0.0000

Data Index: 878086 (C4 (Web Text))

Max Activating Token Index: 330