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

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

Neuron 2331 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2657. Min Act: -0.0000

Data Index: 535748 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1194103 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1202528 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2015. Min Act: -0.0000

Data Index: 473406 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1151179 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2178. Min Act: -0.0000

Data Index: 1226309 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1207409 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1987. Min Act: -0.0000

Data Index: 760396 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1808. Min Act: -0.0000

Data Index: 538152 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1911. Min Act: -0.0000

Data Index: 838944 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1305168 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1487608 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1742. Min Act: -0.0000

Data Index: 246489 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1850. Min Act: -0.0000

Data Index: 418487 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1894. Min Act: -0.0000

Data Index: 20360 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1769. Min Act: -0.0000

Data Index: 766764 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1409147 (Python Code)

Max Activating Token Index: 589

Text #17

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1300164 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1651. Min Act: -0.0000

Data Index: 85793 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1798. Min Act: -0.0000

Data Index: 396531 (C4 (Web Text))

Max Activating Token Index: 237