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

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

Neuron 1821 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2394. Min Act: -0.0000

Data Index: 240423 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1109598 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1578. Min Act: -0.0000

Data Index: 701099 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1931. Min Act: -0.0000

Data Index: 86038 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1143098 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1032469 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1800. Min Act: -0.0000

Data Index: 93903 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1789. Min Act: -0.0000

Data Index: 147224 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1244982 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1687. Min Act: -0.0000

Data Index: 442482 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1750. Min Act: -0.0000

Data Index: 313748 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1608. Min Act: -0.0000

Data Index: 152331 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1583. Min Act: -0.0000

Data Index: 596647 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1402105 (Python Code)

Max Activating Token Index: 206

Text #14

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1604. Min Act: -0.0000

Data Index: 38958 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1625. Min Act: -0.0000

Data Index: 751637 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1148469 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1714. Min Act: -0.0000

Data Index: 727585 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1561. Min Act: -0.0000

Data Index: 929425 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1543. Min Act: -0.0000

Data Index: 227971 (C4 (Web Text))

Max Activating Token Index: 626