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

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

Neuron 4194 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6218. Min Range: -2.6218

Max Act: 2.6218. Min Act: -0.0000

Data Index: 1533638 (Python Code)

Max Activating Token Index: 344

Text #1

Max Range: 2.6218. Min Range: -2.6218

Max Act: 2.4177. Min Act: -0.0000

Data Index: 1626581 (Python Code)

Max Activating Token Index: 744

Text #2

Max Range: 2.6218. Min Range: -2.6218

Max Act: 2.6019. Min Act: -0.0001

Data Index: 1559208 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 2.6218. Min Range: -2.6218

Max Act: 2.1715. Min Act: -0.0000

Data Index: 1622683 (Python Code)

Max Activating Token Index: 660

Text #4

Max Range: 2.6218. Min Range: -2.6218

Max Act: 2.2633. Min Act: -0.0001

Data Index: 1628468 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 2.6218. Min Range: -2.6218

Max Act: 2.2383. Min Act: -0.0000

Data Index: 1436615 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.9876. Min Act: -0.0000

Data Index: 1455148 (Python Code)

Max Activating Token Index: 299

Text #7

Max Range: 2.6218. Min Range: -2.6218

Max Act: 2.1123. Min Act: -0.0000

Data Index: 1596801 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.9952. Min Act: -0.0000

Data Index: 1368052 (Python Code)

Max Activating Token Index: 295

Text #9

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.9720. Min Act: -0.0000

Data Index: 1397827 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 2.6218. Min Range: -2.6218

Max Act: 2.0309. Min Act: -0.0001

Data Index: 1533533 (Python Code)

Max Activating Token Index: 779

Text #11

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.8746. Min Act: -0.0001

Data Index: 1487848 (Python Code)

Max Activating Token Index: 855

Text #12

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.9864. Min Act: -0.0000

Data Index: 1394091 (Python Code)

Max Activating Token Index: 379

Text #13

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.9853. Min Act: -0.0000

Data Index: 1421660 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.9418. Min Act: -0.0000

Data Index: 1453913 (Python Code)

Max Activating Token Index: 617

Text #15

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.9117. Min Act: -0.0000

Data Index: 1418368 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.9108. Min Act: -0.0000

Data Index: 1479253 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.8950. Min Act: -0.0000

Data Index: 1564836 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.9796. Min Act: -0.0000

Data Index: 1617144 (Python Code)

Max Activating Token Index: 286

Text #19

Max Range: 2.6218. Min Range: -2.6218

Max Act: 1.8470. Min Act: -0.0001

Data Index: 1439244 (Python Code)

Max Activating Token Index: 107