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

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

Neuron 4779 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2876. Min Act: -0.0000

Data Index: 475008 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2418. Min Act: -0.0000

Data Index: 361972 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2320. Min Act: -0.0000

Data Index: 148451 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2113. Min Act: -0.0000

Data Index: 603988 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2101. Min Act: -0.0000

Data Index: 858140 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1138290 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2147. Min Act: -0.0000

Data Index: 447080 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1085040 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1997. Min Act: -0.0000

Data Index: 125871 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1989. Min Act: -0.0000

Data Index: 972690 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1866. Min Act: 0.0000

Data Index: 22530 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2000. Min Act: 0.0001

Data Index: 958308 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1900. Min Act: -0.0000

Data Index: 712851 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1874. Min Act: -0.0000

Data Index: 329129 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1030167 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1158871 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1714. Min Act: -0.0000

Data Index: 341681 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1860. Min Act: -0.0000

Data Index: 121070 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1766. Min Act: -0.0000

Data Index: 120605 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1138070 (C4 (Web Text))

Max Activating Token Index: 881