Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 8 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1392621 (Python Code)

Max Activating Token Index: 969

Text #1

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2288. Min Act: -0.0001

Data Index: 1509088 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1473729 (Python Code)

Max Activating Token Index: 836

Text #3

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2158. Min Act: -0.0001

Data Index: 1549656 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1475564 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1642721 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1452579 (Python Code)

Max Activating Token Index: 818

Text #7

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1901. Min Act: -0.0001

Data Index: 1458504 (Python Code)

Max Activating Token Index: 449

Text #8

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1441845 (Python Code)

Max Activating Token Index: 309

Text #9

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1738. Min Act: -0.0001

Data Index: 422939 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1618011 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1831. Min Act: -0.0001

Data Index: 901898 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1794. Min Act: -0.0000

Data Index: 232867 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1167751 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1026619 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1374340 (Python Code)

Max Activating Token Index: 275

Text #16

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1666. Min Act: -0.0001

Data Index: 1576436 (Python Code)

Max Activating Token Index: 220

Text #17

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1671. Min Act: -0.0001

Data Index: 1578232 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1705. Min Act: -0.0001

Data Index: 1468946 (Python Code)

Max Activating Token Index: 744

Text #19

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1610167 (Python Code)

Max Activating Token Index: 456