Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1831 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1382. Min Act: -0.0001

Data Index: 164446 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1127789 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0876. Min Act: -0.0001

Data Index: 670880 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1011. Min Act: -0.0001

Data Index: 85730 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0875. Min Act: -0.0001

Data Index: 105852 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0825. Min Act: -0.0001

Data Index: 936322 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0738. Min Act: -0.0001

Data Index: 120475 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0905. Min Act: -0.0001

Data Index: 481885 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0747. Min Act: -0.0001

Data Index: 958790 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0899. Min Act: -0.0001

Data Index: 604907 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0905. Min Act: -0.0001

Data Index: 776818 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1122910 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0796. Min Act: -0.0001

Data Index: 547109 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1249768 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1202948 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1134762 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0814. Min Act: -0.0001

Data Index: 841049 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1601666 (Python Code)

Max Activating Token Index: 702

Text #18

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0786. Min Act: -0.0001

Data Index: 684216 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0600. Min Act: -0.0001

Data Index: 614704 (C4 (Web Text))

Max Activating Token Index: 701