Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2836 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.8377. Min Act: -0.0001

Data Index: 1526783 (Python Code)

Max Activating Token Index: 775

Text #1

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.7007. Min Act: -0.0001

Data Index: 1556179 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.6725. Min Act: -0.0001

Data Index: 1436653 (Python Code)

Max Activating Token Index: 192

Text #3

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.6321. Min Act: -0.0001

Data Index: 1646649 (Python Code)

Max Activating Token Index: 884

Text #4

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5295. Min Act: -0.0001

Data Index: 1396504 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5807. Min Act: -0.0001

Data Index: 1455432 (Python Code)

Max Activating Token Index: 204

Text #6

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5446. Min Act: -0.0001

Data Index: 1527630 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1654697 (Python Code)

Max Activating Token Index: 307

Text #8

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.4544. Min Act: -0.0000

Data Index: 799113 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.4309. Min Act: -0.0001

Data Index: 1569899 (Python Code)

Max Activating Token Index: 840

Text #10

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.4410. Min Act: -0.0001

Data Index: 1533365 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.3971. Min Act: -0.0001

Data Index: 795800 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.4222. Min Act: -0.0001

Data Index: 1385823 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.4159. Min Act: -0.0001

Data Index: 1621397 (Python Code)

Max Activating Token Index: 725

Text #14

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.3863. Min Act: -0.0001

Data Index: 1530108 (Python Code)

Max Activating Token Index: 795

Text #15

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.3657. Min Act: -0.0001

Data Index: 103703 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.3776. Min Act: -0.0001

Data Index: 1384090 (Python Code)

Max Activating Token Index: 128

Text #17

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.3228. Min Act: -0.0001

Data Index: 1614656 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.3582. Min Act: -0.0001

Data Index: 479747 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1314679 (C4 (Web Text))

Max Activating Token Index: 274