Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1915 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1429730 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1417862 (Python Code)

Max Activating Token Index: 607

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1425901 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1628071 (Python Code)

Max Activating Token Index: 798

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1441503 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1451751 (Python Code)

Max Activating Token Index: 403

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1552366 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1556750 (Python Code)

Max Activating Token Index: 904

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1571767 (Python Code)

Max Activating Token Index: 660

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1421362 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1423443 (Python Code)

Max Activating Token Index: 844

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1496017 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1628670 (Python Code)

Max Activating Token Index: 695

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1619528 (Python Code)

Max Activating Token Index: 785

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1551736 (Python Code)

Max Activating Token Index: 295

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1643603 (Python Code)

Max Activating Token Index: 599

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1649704 (Python Code)

Max Activating Token Index: 194

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1526824 (Python Code)

Max Activating Token Index: 408

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1383683 (Python Code)

Max Activating Token Index: 618

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1480262 (Python Code)

Max Activating Token Index: 854