Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3741 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5392. Min Act: -0.0000

Data Index: 762845 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5725. Min Act: -0.0000

Data Index: 149481 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5567. Min Act: -0.0000

Data Index: 539529 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5116. Min Act: -0.0000

Data Index: 861156 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5428. Min Act: -0.0000

Data Index: 870409 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1002507 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5047. Min Act: -0.0000

Data Index: 686152 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1213378 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4833. Min Act: -0.0000

Data Index: 470107 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4529. Min Act: -0.0000

Data Index: 462841 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4466. Min Act: -0.0000

Data Index: 720046 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1108444 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4557. Min Act: -0.0000

Data Index: 8638 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4488. Min Act: -0.0000

Data Index: 548995 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1124952 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4346. Min Act: -0.0000

Data Index: 613800 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4278. Min Act: -0.0000

Data Index: 893164 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3934. Min Act: -0.0000

Data Index: 648821 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4111. Min Act: -0.0000

Data Index: 734993 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3969. Min Act: -0.0000

Data Index: 724287 (C4 (Web Text))

Max Activating Token Index: 976