Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2891 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1124589 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1347611 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.7420. Min Act: -0.0000

Data Index: 663370 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.7263. Min Act: -0.0000

Data Index: 210358 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.7372. Min Act: -0.0000

Data Index: 774906 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1195073 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1192681 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6782. Min Act: -0.0000

Data Index: 113228 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1332308 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6551. Min Act: -0.0000

Data Index: 215019 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6321. Min Act: -0.0000

Data Index: 227527 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1192776 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1013359 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6267. Min Act: -0.0000

Data Index: 210164 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.5983. Min Act: -0.0000

Data Index: 359174 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.5764. Min Act: -0.0000

Data Index: 972156 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.5628. Min Act: -0.0000

Data Index: 697491 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.5927. Min Act: -0.0000

Data Index: 976774 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6076. Min Act: -0.0000

Data Index: 596102 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.5889. Min Act: -0.0000

Data Index: 509636 (C4 (Web Text))

Max Activating Token Index: 835