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

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

Neuron 431 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.7556. Min Act: 0.0000

Data Index: 1002910 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.7036. Min Act: -0.0000

Data Index: 926109 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.6239. Min Act: 0.0000

Data Index: 905696 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5968. Min Act: 0.0000

Data Index: 73326 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5966. Min Act: -0.0000

Data Index: 502929 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5722. Min Act: 0.0002

Data Index: 1165692 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5633. Min Act: -0.0000

Data Index: 654492 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5777. Min Act: 0.0000

Data Index: 214472 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5697. Min Act: -0.0000

Data Index: 560715 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5691. Min Act: -0.0000

Data Index: 897868 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5805. Min Act: 0.0001

Data Index: 750387 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5717. Min Act: -0.0000

Data Index: 880117 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5377. Min Act: 0.0001

Data Index: 1050843 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5501. Min Act: 0.0000

Data Index: 968221 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5486. Min Act: 0.0000

Data Index: 1019414 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5590. Min Act: -0.0000

Data Index: 787801 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1319736 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5479. Min Act: 0.0000

Data Index: 12876 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5194. Min Act: -0.0000

Data Index: 598339 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1060837 (C4 (Web Text))

Max Activating Token Index: 389