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

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

Neuron 430 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1055484 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0682. Min Act: -0.0002

Data Index: 798829 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1441603 (Python Code)

Max Activating Token Index: 825

Text #3

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0708. Min Act: -0.0002

Data Index: 505738 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1409822 (Python Code)

Max Activating Token Index: 713

Text #5

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0647. Min Act: -0.0002

Data Index: 610984 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0715. Min Act: -0.0002

Data Index: 365017 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1523928 (Python Code)

Max Activating Token Index: 895

Text #8

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1495643 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0634. Min Act: -0.0002

Data Index: 860304 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1391693 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1384298 (Python Code)

Max Activating Token Index: 60

Text #12

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1467690 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1365854 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1631382 (Python Code)

Max Activating Token Index: 674

Text #15

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0655. Min Act: -0.0002

Data Index: 116363 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0658. Min Act: -0.0002

Data Index: 749494 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1413640 (Python Code)

Max Activating Token Index: 285

Text #18

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0670. Min Act: -0.0002

Data Index: 287211 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1393912 (Python Code)

Max Activating Token Index: 14