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

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

Neuron 3058 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0497. Min Act: -0.0003

Data Index: 997491 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0504. Min Act: -0.0003

Data Index: 78905 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0467. Min Act: -0.0003

Data Index: 183875 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0471. Min Act: -0.0003

Data Index: 934957 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1198121 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0455. Min Act: -0.0002

Data Index: 891759 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0478. Min Act: -0.0003

Data Index: 742202 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0466. Min Act: -0.0003

Data Index: 312571 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0459. Min Act: -0.0003

Data Index: 53814 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0433. Min Act: -0.0003

Data Index: 801679 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0434. Min Act: -0.0003

Data Index: 385412 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1167838 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0435. Min Act: -0.0003

Data Index: 592575 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0419. Min Act: -0.0003

Data Index: 884025 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0438. Min Act: -0.0003

Data Index: 658012 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0417. Min Act: -0.0003

Data Index: 223768 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0425. Min Act: -0.0003

Data Index: 733523 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0413. Min Act: -0.0003

Data Index: 682719 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1113155 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1272082 (C4 (Web Text))

Max Activating Token Index: 721