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

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

Neuron 4443 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: 0.2219. Min Range: -0.2219

Max Act: 0.2219. Min Act: 0.0000

Data Index: 839040 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1867. Min Act: -0.0000

Data Index: 193502 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1772. Min Act: 0.0001

Data Index: 890715 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1220156 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1746. Min Act: -0.0000

Data Index: 323510 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1744. Min Act: -0.0000

Data Index: 965705 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1725. Min Act: 0.0000

Data Index: 491624 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1732. Min Act: -0.0000

Data Index: 343164 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1176243 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1617. Min Act: -0.0000

Data Index: 142036 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1509. Min Act: -0.0000

Data Index: 486633 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1013979 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1533. Min Act: -0.0000

Data Index: 62676 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1482. Min Act: -0.0000

Data Index: 392032 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1530. Min Act: -0.0000

Data Index: 431523 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1493. Min Act: -0.0000

Data Index: 1249519 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1492. Min Act: -0.0000

Data Index: 987796 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1315. Min Act: 0.0000

Data Index: 1162600 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1420. Min Act: -0.0000

Data Index: 120475 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1468. Min Act: -0.0000

Data Index: 865221 (C4 (Web Text))

Max Activating Token Index: 917