Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 800 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1177. Min Act: -0.0001

Data Index: 411868 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1118. Min Act: -0.0001

Data Index: 18006 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1337753 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1010254 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1332764 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1322580 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0812. Min Act: -0.0001

Data Index: 420866 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0824. Min Act: -0.0001

Data Index: 176058 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0789. Min Act: -0.0001

Data Index: 221169 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0793. Min Act: -0.0001

Data Index: 781140 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0806. Min Act: -0.0001

Data Index: 491511 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0809. Min Act: -0.0001

Data Index: 495239 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0756. Min Act: -0.0001

Data Index: 97353 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1346270 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1189761 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1185198 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1347625 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0769. Min Act: -0.0001

Data Index: 338137 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0750. Min Act: -0.0001

Data Index: 889206 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0722. Min Act: -0.0001

Data Index: 684604 (C4 (Web Text))

Max Activating Token Index: 658