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

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

Neuron 2169 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0001

Data Index: 1025981 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1164. Min Act: -0.0001

Data Index: 406328 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1090. Min Act: -0.0001

Data Index: 107891 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1057. Min Act: -0.0000

Data Index: 571924 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1305416 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0989. Min Act: -0.0001

Data Index: 261708 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0969. Min Act: -0.0001

Data Index: 961450 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0874. Min Act: -0.0000

Data Index: 573156 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1087070 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1199177 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0867. Min Act: -0.0001

Data Index: 468197 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0895. Min Act: -0.0000

Data Index: 252579 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1253927 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0949. Min Act: -0.0001

Data Index: 687224 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0931. Min Act: -0.0001

Data Index: 982069 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1044688 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1228410 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0899. Min Act: -0.0000

Data Index: 219287 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1045965 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0830. Min Act: -0.0001

Data Index: 281176 (C4 (Web Text))

Max Activating Token Index: 172