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

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

Neuron 2218 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.6992. Min Act: -0.0000

Data Index: 1646839 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.5444. Min Act: -0.0000

Data Index: 1469452 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.3665. Min Act: -0.0000

Data Index: 1612502 (Python Code)

Max Activating Token Index: 969

Text #3

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.2888. Min Act: -0.0000

Data Index: 1575177 (Python Code)

Max Activating Token Index: 182

Text #4

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.3918. Min Act: -0.0000

Data Index: 1435747 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.1233. Min Act: -0.0000

Data Index: 1585377 (Python Code)

Max Activating Token Index: 308

Text #6

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.3557. Min Act: -0.0000

Data Index: 1417919 (Python Code)

Max Activating Token Index: 226

Text #7

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.3435. Min Act: -0.0000

Data Index: 1370638 (Python Code)

Max Activating Token Index: 52

Text #8

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.1879. Min Act: -0.0000

Data Index: 1649854 (Python Code)

Max Activating Token Index: 994

Text #9

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.2056. Min Act: -0.0000

Data Index: 1428732 (Python Code)

Max Activating Token Index: 991

Text #10

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.1773. Min Act: -0.0000

Data Index: 1388218 (Python Code)

Max Activating Token Index: 719

Text #11

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.1786. Min Act: -0.0000

Data Index: 1602960 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.1717. Min Act: -0.0000

Data Index: 1559742 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.0310. Min Act: -0.0000

Data Index: 1629648 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.2481. Min Act: -0.0000

Data Index: 1521518 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 2.6992. Min Range: -2.6992

Max Act: 1.9954. Min Act: -0.0000

Data Index: 1462101 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.0950. Min Act: -0.0000

Data Index: 1388647 (Python Code)

Max Activating Token Index: 332

Text #17

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.0995. Min Act: -0.0000

Data Index: 1572813 (Python Code)

Max Activating Token Index: 506

Text #18

Max Range: 2.6992. Min Range: -2.6992

Max Act: 1.9865. Min Act: -0.0000

Data Index: 1603617 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 2.6992. Min Range: -2.6992

Max Act: 2.0936. Min Act: -0.0000

Data Index: 1467124 (Python Code)

Max Activating Token Index: 299