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

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

Neuron 3301 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: 0.1607. Min Range: -0.1607

Max Act: 0.1607. Min Act: -0.0001

Data Index: 166492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1328682 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1250. Min Act: -0.0001

Data Index: 807982 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1057312 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1190. Min Act: -0.0001

Data Index: 329137 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1316388 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1176. Min Act: -0.0001

Data Index: 669860 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1043. Min Act: -0.0001

Data Index: 450145 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0673. Min Act: -0.0001

Data Index: 243487 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1225545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0909. Min Act: -0.0001

Data Index: 538167 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0719. Min Act: -0.0001

Data Index: 950642 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0800. Min Act: -0.0001

Data Index: 242290 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0889. Min Act: -0.0001

Data Index: 659080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1273998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0770. Min Act: -0.0001

Data Index: 772870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0729. Min Act: -0.0001

Data Index: 257465 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0783. Min Act: -0.0001

Data Index: 242411 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0666. Min Act: -0.0001

Data Index: 464082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0878. Min Act: -0.0001

Data Index: 752321 (C4 (Web Text))

Max Activating Token Index: 1023