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

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

Neuron 3723 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1331. Min Act: -0.0000

Data Index: 573868 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1277697 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1131. Min Act: -0.0000

Data Index: 343622 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0990. Min Act: -0.0000

Data Index: 736208 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1076. Min Act: -0.0000

Data Index: 582865 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1049. Min Act: -0.0000

Data Index: 573409 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1051. Min Act: -0.0000

Data Index: 530442 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1019. Min Act: -0.0000

Data Index: 559618 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0985. Min Act: -0.0000

Data Index: 964781 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0977. Min Act: -0.0000

Data Index: 183955 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1255105 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1331875 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1072850 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0955. Min Act: -0.0000

Data Index: 87667 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0921. Min Act: -0.0000

Data Index: 772256 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0926. Min Act: -0.0000

Data Index: 903699 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0944. Min Act: -0.0000

Data Index: 545308 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1101923 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0932. Min Act: -0.0000

Data Index: 339967 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0901. Min Act: 0.0000

Data Index: 771165 (C4 (Web Text))

Max Activating Token Index: 668