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

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

Neuron 4897 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: 0.0721. Min Range: -0.0721

Max Act: 0.0718. Min Act: -0.0000

Data Index: 699614 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1565141 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1532259 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0638. Min Act: -0.0000

Data Index: 757099 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0655. Min Act: -0.0000

Data Index: 86230 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0617. Min Act: -0.0000

Data Index: 600358 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0659. Min Act: -0.0000

Data Index: 825694 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0616. Min Act: -0.0000

Data Index: 624005 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1285017 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1485177 (Python Code)

Max Activating Token Index: 859

Text #10

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1576018 (Python Code)

Max Activating Token Index: 882

Text #11

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1492846 (Python Code)

Max Activating Token Index: 947

Text #12

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0614. Min Act: -0.0000

Data Index: 470974 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0596. Min Act: -0.0000

Data Index: 886311 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1367110 (Python Code)

Max Activating Token Index: 773

Text #15

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1015059 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0601. Min Act: -0.0000

Data Index: 306905 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0596. Min Act: -0.0000

Data Index: 519233 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1308748 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1363516 (Python Code)

Max Activating Token Index: 567