Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3244 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.3021. Min Act: -0.0001

Data Index: 1158231 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2026. Min Act: -0.0001

Data Index: 1513639 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2134. Min Act: -0.0001

Data Index: 282160 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1739. Min Act: -0.0001

Data Index: 237493 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1737. Min Act: -0.0001

Data Index: 674738 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1601. Min Act: -0.0001

Data Index: 633742 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1682. Min Act: -0.0001

Data Index: 271689 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1303179 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1562. Min Act: -0.0001

Data Index: 547236 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1497633 (Python Code)

Max Activating Token Index: 714

Text #10

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1135811 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1138302 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1287973 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1527. Min Act: -0.0001

Data Index: 26296 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1596. Min Act: -0.0001

Data Index: 513958 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1452. Min Act: -0.0001

Data Index: 495332 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1405547 (Python Code)

Max Activating Token Index: 122

Text #17

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1292568 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1454715 (Python Code)

Max Activating Token Index: 452

Text #19

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1379824 (Python Code)

Max Activating Token Index: 424