Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2414 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0001

Data Index: 112863 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1416306 (Python Code)

Max Activating Token Index: 783

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1260087 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0826. Min Act: -0.0001

Data Index: 665098 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0802. Min Act: -0.0001

Data Index: 302717 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0757. Min Act: -0.0001

Data Index: 414093 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0779. Min Act: -0.0000

Data Index: 702048 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0800. Min Act: -0.0001

Data Index: 58261 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0800. Min Act: -0.0001

Data Index: 314006 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1204426 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0763. Min Act: -0.0001

Data Index: 292697 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0733. Min Act: -0.0001

Data Index: 742275 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0697. Min Act: -0.0001

Data Index: 335514 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1594888 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1097125 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0663. Min Act: -0.0001

Data Index: 313861 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1187054 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0652. Min Act: -0.0001

Data Index: 595479 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0718. Min Act: -0.0001

Data Index: 898396 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0722. Min Act: -0.0001

Data Index: 326552 (C4 (Web Text))

Max Activating Token Index: 778