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

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

Neuron 5486 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0001

Data Index: 21925 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0866. Min Act: -0.0001

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0810. Min Act: -0.0001

Data Index: 78465 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0798. Min Act: -0.0001

Data Index: 827260 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1177482 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1225065 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0672. Min Act: -0.0001

Data Index: 157500 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0747. Min Act: -0.0001

Data Index: 319695 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0709. Min Act: -0.0001

Data Index: 659885 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1223263 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0683. Min Act: -0.0001

Data Index: 662693 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0652. Min Act: -0.0001

Data Index: 319293 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0587. Min Act: -0.0001

Data Index: 406737 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0504. Min Act: -0.0001

Data Index: 262754 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0594. Min Act: -0.0001

Data Index: 646064 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1240691 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0476. Min Act: -0.0001

Data Index: 141641 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0541. Min Act: -0.0001

Data Index: 762326 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1133300 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1275421 (C4 (Web Text))

Max Activating Token Index: 321