Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 776 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1562. Min Act: -0.0002

Data Index: 596009 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1486. Min Act: -0.0002

Data Index: 252524 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1514. Min Act: -0.0002

Data Index: 680092 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1508. Min Act: -0.0002

Data Index: 1106784 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1503. Min Act: -0.0002

Data Index: 823790 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1496. Min Act: -0.0002

Data Index: 1093230 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1416. Min Act: -0.0002

Data Index: 1036904 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1461. Min Act: -0.0002

Data Index: 1355328 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1414. Min Act: -0.0002

Data Index: 582000 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1381. Min Act: -0.0002

Data Index: 718570 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1546. Min Act: -0.0002

Data Index: 108289 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1454. Min Act: -0.0002

Data Index: 1238753 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1511. Min Act: -0.0002

Data Index: 688678 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1422. Min Act: -0.0002

Data Index: 1133757 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1422. Min Act: -0.0002

Data Index: 113701 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1452. Min Act: -0.0002

Data Index: 504344 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1503. Min Act: -0.0002

Data Index: 20500 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1494. Min Act: -0.0002

Data Index: 1153106 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1372. Min Act: -0.0002

Data Index: 168028 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1447. Min Act: -0.0002

Data Index: 850299 (C4 (Web Text))

Max Activating Token Index: 716