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

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

Neuron 5415 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0653. Min Act: -0.0002

Data Index: 174691 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0669. Min Act: -0.0002

Data Index: 714314 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0637. Min Act: -0.0002

Data Index: 894350 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0625. Min Act: -0.0002

Data Index: 418454 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0601. Min Act: -0.0002

Data Index: 592001 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0601. Min Act: -0.0002

Data Index: 229970 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0564. Min Act: -0.0002

Data Index: 182481 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0586. Min Act: -0.0002

Data Index: 966646 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1208076 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0578. Min Act: -0.0002

Data Index: 597821 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0549. Min Act: -0.0002

Data Index: 98391 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0550. Min Act: -0.0002

Data Index: 819170 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0546. Min Act: -0.0002

Data Index: 456419 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1045706 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0514. Min Act: -0.0002

Data Index: 726596 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1146017 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0525. Min Act: -0.0002

Data Index: 576168 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1405207 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0496. Min Act: -0.0002

Data Index: 107808 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0516. Min Act: -0.0002

Data Index: 984504 (C4 (Web Text))

Max Activating Token Index: 169