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

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

Neuron 2783 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8893. Min Act: -0.0000

Data Index: 934511 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8096. Min Act: -0.0000

Data Index: 338373 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7073. Min Act: -0.0000

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7849. Min Act: -0.0000

Data Index: 516652 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7021. Min Act: -0.0000

Data Index: 330102 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.6681. Min Act: -0.0000

Data Index: 828973 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.6791. Min Act: -0.0000

Data Index: 477323 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.5802. Min Act: -0.0000

Data Index: 570442 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.5762. Min Act: -0.0000

Data Index: 615538 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.5565. Min Act: -0.0000

Data Index: 755143 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.5557. Min Act: -0.0000

Data Index: 461056 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1133398 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.5517. Min Act: -0.0000

Data Index: 97727 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.5163. Min Act: -0.0000

Data Index: 603089 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.5048. Min Act: -0.0000

Data Index: 615273 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.5049. Min Act: -0.0000

Data Index: 256933 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.4805. Min Act: -0.0000

Data Index: 496075 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.4727. Min Act: -0.0000

Data Index: 815479 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.4611. Min Act: -0.0000

Data Index: 401580 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.4323. Min Act: -0.0000

Data Index: 149760 (C4 (Web Text))

Max Activating Token Index: 930