Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 65 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3457. Min Act: -0.0000

Data Index: 283451 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1539694 (Python Code)

Max Activating Token Index: 647

Text #2

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1314484 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1088256 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2175. Min Act: 0.0000

Data Index: 182069 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1566255 (Python Code)

Max Activating Token Index: 709

Text #6

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1104726 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1638666 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1984. Min Act: -0.0000

Data Index: 849195 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2046. Min Act: 0.0000

Data Index: 1329876 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1286039 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1585134 (Python Code)

Max Activating Token Index: 118

Text #12

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1805. Min Act: 0.0000

Data Index: 336139 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1916. Min Act: -0.0000

Data Index: 643123 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1890. Min Act: -0.0000

Data Index: 866937 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1446117 (Python Code)

Max Activating Token Index: 681

Text #16

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1440032 (Python Code)

Max Activating Token Index: 598

Text #17

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1599198 (Python Code)

Max Activating Token Index: 539

Text #18

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1581249 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1524111 (Python Code)

Max Activating Token Index: 20