Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 329 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.2039. Min Act: -0.0002

Data Index: 1205120 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1957. Min Act: -0.0003

Data Index: 974833 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1828. Min Act: -0.0003

Data Index: 74216 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1792. Min Act: -0.0003

Data Index: 951532 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1768. Min Act: -0.0003

Data Index: 44398 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1804. Min Act: -0.0003

Data Index: 987570 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1694. Min Act: -0.0003

Data Index: 788422 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1644. Min Act: -0.0003

Data Index: 908406 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1634. Min Act: -0.0002

Data Index: 568640 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1565. Min Act: -0.0003

Data Index: 854261 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1603. Min Act: -0.0003

Data Index: 262698 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1601. Min Act: -0.0003

Data Index: 435365 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1577. Min Act: -0.0003

Data Index: 1036097 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1578. Min Act: -0.0003

Data Index: 869370 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1511. Min Act: -0.0003

Data Index: 376268 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1565. Min Act: -0.0003

Data Index: 897301 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1555. Min Act: -0.0003

Data Index: 772484 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1499. Min Act: -0.0003

Data Index: 542589 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1549. Min Act: -0.0003

Data Index: 798083 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.2039. Min Range: -0.2039

Max Act: 0.1534. Min Act: -0.0003

Data Index: 697043 (C4 (Web Text))

Max Activating Token Index: 290