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

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

Neuron 3516 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1334. Min Act: -0.0001

Data Index: 1095456 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1106. Min Act: -0.0001

Data Index: 399136 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1067. Min Act: -0.0001

Data Index: 891906 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1237. Min Act: -0.0001

Data Index: 195992 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1141. Min Act: -0.0001

Data Index: 91239 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1085105 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0857. Min Act: -0.0001

Data Index: 567061 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0926. Min Act: -0.0001

Data Index: 504508 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0842. Min Act: -0.0001

Data Index: 768835 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1039. Min Act: -0.0001

Data Index: 72415 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0887. Min Act: -0.0002

Data Index: 996133 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0849. Min Act: -0.0001

Data Index: 28974 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0858. Min Act: -0.0001

Data Index: 885434 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0712. Min Act: -0.0001

Data Index: 727001 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0798. Min Act: -0.0001

Data Index: 678833 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0830. Min Act: -0.0001

Data Index: 245314 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0775. Min Act: -0.0001

Data Index: 350114 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0694. Min Act: -0.0001

Data Index: 160561 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1278161 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0777. Min Act: -0.0001

Data Index: 231959 (C4 (Web Text))

Max Activating Token Index: 120