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

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

Neuron 478 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.1032. Min Act: -0.0000

Data Index: 546806 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0730. Min Act: -0.0001

Data Index: 276296 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0771. Min Act: -0.0000

Data Index: 335450 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1522152 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0630. Min Act: -0.0000

Data Index: 121747 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0558. Min Act: -0.0001

Data Index: 248836 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0605. Min Act: -0.0000

Data Index: 380439 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0648. Min Act: -0.0000

Data Index: 264449 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0494. Min Act: -0.0001

Data Index: 376297 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1332036 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1640482 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0550. Min Act: -0.0001

Data Index: 262743 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1592036 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0533. Min Act: -0.0001

Data Index: 160052 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1071395 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1608787 (Python Code)

Max Activating Token Index: 910

Text #16

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0581. Min Act: -0.0001

Data Index: 727470 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0532. Min Act: -0.0000

Data Index: 1583540 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1275640 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0488. Min Act: -0.0001

Data Index: 149472 (C4 (Web Text))

Max Activating Token Index: 766