Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1726. Min Act: -0.0000

Data Index: 755431 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1239. Min Act: -0.0000

Data Index: 782652 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1096. Min Act: -0.0000

Data Index: 941999 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0867. Min Act: -0.0000

Data Index: 891298 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0844. Min Act: -0.0000

Data Index: 927382 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1628258 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0780. Min Act: -0.0000

Data Index: 938607 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0757. Min Act: -0.0000

Data Index: 286898 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0753. Min Act: -0.0000

Data Index: 987866 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1270774 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0740. Min Act: -0.0000

Data Index: 292107 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1599384 (Python Code)

Max Activating Token Index: 836

Text #12

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0695. Min Act: -0.0000

Data Index: 65360 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1067015 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1537150 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0644. Min Act: -0.0000

Data Index: 967868 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0674. Min Act: -0.0000

Data Index: 1022137 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1436081 (Python Code)

Max Activating Token Index: 453

Text #18

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1117701 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1627723 (Python Code)

Max Activating Token Index: 55