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

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

Neuron 1625 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2352. Min Act: -0.0000

Data Index: 878504 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2099. Min Act: -0.0000

Data Index: 551041 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2104. Min Act: -0.0000

Data Index: 763263 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1944. Min Act: -0.0000

Data Index: 981170 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1806. Min Act: -0.0000

Data Index: 241165 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1802. Min Act: -0.0000

Data Index: 635382 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1702. Min Act: -0.0000

Data Index: 364095 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1635. Min Act: -0.0000

Data Index: 732684 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1001931 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1597. Min Act: -0.0000

Data Index: 16596 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1596. Min Act: -0.0000

Data Index: 315414 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1567. Min Act: -0.0000

Data Index: 861965 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1458. Min Act: -0.0000

Data Index: 85455 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1440. Min Act: -0.0000

Data Index: 134315 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1441. Min Act: -0.0000

Data Index: 230069 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1363. Min Act: -0.0000

Data Index: 885969 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1404. Min Act: -0.0000

Data Index: 691537 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1443. Min Act: -0.0000

Data Index: 284842 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1322. Min Act: -0.0000

Data Index: 52096 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1416. Min Act: -0.0000

Data Index: 540051 (C4 (Web Text))

Max Activating Token Index: 971