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

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

Neuron 2008 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: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1565166 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1560418 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1416918 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1569144 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1484713 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1525278 (Python Code)

Max Activating Token Index: 862

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1627573 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1553885 (Python Code)

Max Activating Token Index: 678

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1190549 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1434862 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1531976 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1491520 (Python Code)

Max Activating Token Index: 841

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1404448 (Python Code)

Max Activating Token Index: 85

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1606700 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1401824 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1529077 (Python Code)

Max Activating Token Index: 836

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1514676 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1376202 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0561. Min Act: -0.0004

Data Index: 1635232 (Python Code)

Max Activating Token Index: 248

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1441611 (Python Code)

Max Activating Token Index: 67