Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3987 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1865. Min Act: -0.0000

Data Index: 49122 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1816. Min Act: -0.0000

Data Index: 446335 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1743. Min Act: -0.0001

Data Index: 598502 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1754. Min Act: -0.0001

Data Index: 865395 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1701. Min Act: -0.0001

Data Index: 35679 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1301305 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1658. Min Act: -0.0001

Data Index: 292636 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1597. Min Act: -0.0001

Data Index: 213990 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1649. Min Act: -0.0001

Data Index: 866421 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1508. Min Act: -0.0001

Data Index: 16425 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1545. Min Act: -0.0001

Data Index: 538388 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1545. Min Act: -0.0001

Data Index: 506116 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1562. Min Act: -0.0001

Data Index: 423522 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1455. Min Act: -0.0000

Data Index: 910468 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1502. Min Act: -0.0000

Data Index: 730953 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1440. Min Act: -0.0000

Data Index: 784594 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1503. Min Act: -0.0001

Data Index: 1027324 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1485. Min Act: -0.0001

Data Index: 467838 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1478. Min Act: -0.0000

Data Index: 964872 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1466. Min Act: -0.0000

Data Index: 879665 (C4 (Web Text))

Max Activating Token Index: 298