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

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

Neuron 687 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1185008 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1908. Min Act: 0.0000

Data Index: 1211774 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1868. Min Act: -0.0000

Data Index: 265300 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1677. Min Act: 0.0000

Data Index: 915304 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1928. Min Act: -0.0000

Data Index: 607962 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1672. Min Act: -0.0001

Data Index: 693261 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1824. Min Act: -0.0001

Data Index: 589474 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1720. Min Act: -0.0001

Data Index: 774790 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1896. Min Act: -0.0000

Data Index: 519809 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1676. Min Act: -0.0001

Data Index: 963540 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1644. Min Act: -0.0001

Data Index: 538969 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1599. Min Act: -0.0000

Data Index: 529521 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1688. Min Act: -0.0000

Data Index: 110531 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1648. Min Act: -0.0001

Data Index: 164678 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1574. Min Act: -0.0000

Data Index: 570880 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1074002 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1593174 (Python Code)

Max Activating Token Index: 566

Text #17

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1613. Min Act: -0.0001

Data Index: 42956 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1554. Min Act: -0.0001

Data Index: 847569 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1532. Min Act: -0.0001

Data Index: 310481 (C4 (Web Text))

Max Activating Token Index: 872