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

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

Neuron 171 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1844. Min Act: -0.0000

Data Index: 497191 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1532618 (Python Code)

Max Activating Token Index: 403

Text #2

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1721. Min Act: -0.0000

Data Index: 226657 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1852. Min Act: -0.0000

Data Index: 854509 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1757. Min Act: -0.0000

Data Index: 9070 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1617. Min Act: -0.0000

Data Index: 19674 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1706. Min Act: -0.0000

Data Index: 270418 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1401396 (Python Code)

Max Activating Token Index: 148

Text #8

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1559590 (Python Code)

Max Activating Token Index: 900

Text #9

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1353772 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1587. Min Act: -0.0000

Data Index: 157595 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1521638 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1224348 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1168018 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1281626 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1474. Min Act: -0.0000

Data Index: 812669 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1472. Min Act: 0.0000

Data Index: 1365199 (Python Code)

Max Activating Token Index: 937

Text #17

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1469. Min Act: -0.0000

Data Index: 1475862 (Python Code)

Max Activating Token Index: 981

Text #18

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1500832 (Python Code)

Max Activating Token Index: 881

Text #19

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1005989 (C4 (Web Text))

Max Activating Token Index: 702