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

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

Neuron 4977 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2835. Min Act: -0.0000

Data Index: 481585 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2308. Min Act: -0.0000

Data Index: 491035 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2060. Min Act: -0.0000

Data Index: 157107 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2006. Min Act: -0.0000

Data Index: 72652 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2026. Min Act: -0.0000

Data Index: 783640 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1040389 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1182746 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1751. Min Act: -0.0000

Data Index: 412530 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1687. Min Act: -0.0000

Data Index: 178611 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1346849 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1667. Min Act: -0.0000

Data Index: 495521 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1264767 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1666. Min Act: -0.0000

Data Index: 100637 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1023772 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1644. Min Act: -0.0000

Data Index: 348123 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1585. Min Act: -0.0000

Data Index: 420677 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1670. Min Act: -0.0000

Data Index: 379447 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1555. Min Act: -0.0000

Data Index: 614783 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1548. Min Act: -0.0000

Data Index: 114693 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1042100 (C4 (Web Text))

Max Activating Token Index: 959