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

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

Neuron 2326 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: 0.8604. Min Range: -0.8604

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1465975 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1656756 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1607144 (Python Code)

Max Activating Token Index: 219

Text #3

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1377530 (Python Code)

Max Activating Token Index: 465

Text #4

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1492946 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1626209 (Python Code)

Max Activating Token Index: 59

Text #6

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1655874 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1628499 (Python Code)

Max Activating Token Index: 56

Text #8

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1579155 (Python Code)

Max Activating Token Index: 610

Text #9

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1400884 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1494882 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4638. Min Act: -0.0000

Data Index: 583654 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1616813 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1507515 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1506859 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1401493 (Python Code)

Max Activating Token Index: 1010

Text #16

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4550. Min Act: -0.0000

Data Index: 217711 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1468304 (Python Code)

Max Activating Token Index: 637

Text #18

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1119632 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4153. Min Act: -0.0000

Data Index: 130345 (C4 (Web Text))

Max Activating Token Index: 685