Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1534 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1444. Min Act: -0.0000

Data Index: 788317 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1193653 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0880. Min Act: -0.0000

Data Index: 75338 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0804. Min Act: -0.0000

Data Index: 853166 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0776. Min Act: -0.0000

Data Index: 372870 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0766. Min Act: -0.0001

Data Index: 149293 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0755. Min Act: -0.0001

Data Index: 560915 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1049056 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0734. Min Act: -0.0000

Data Index: 315547 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0693. Min Act: -0.0001

Data Index: 430978 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0717. Min Act: -0.0001

Data Index: 462136 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1010731 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0732. Min Act: -0.0000

Data Index: 162670 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1242506 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0668. Min Act: -0.0000

Data Index: 455356 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1278772 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1258692 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1251064 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0651. Min Act: -0.0001

Data Index: 892417 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1271184 (C4 (Web Text))

Max Activating Token Index: 672