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

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

Neuron 3790 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2807. Min Act: -0.0000

Data Index: 245847 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2552. Min Act: -0.0000

Data Index: 819474 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2230. Min Act: -0.0000

Data Index: 278271 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1167590 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2434. Min Act: -0.0000

Data Index: 913829 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2166. Min Act: -0.0000

Data Index: 306917 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2365. Min Act: -0.0000

Data Index: 352986 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2130. Min Act: -0.0000

Data Index: 308745 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2030. Min Act: -0.0000

Data Index: 6021 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1057190 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1347504 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1141476 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1913. Min Act: -0.0000

Data Index: 887691 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1922. Min Act: -0.0000

Data Index: 311433 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1974. Min Act: -0.0000

Data Index: 136067 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1898. Min Act: -0.0000

Data Index: 27212 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1283391 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1889. Min Act: -0.0000

Data Index: 325679 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1853. Min Act: -0.0000

Data Index: 680320 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1200881 (C4 (Web Text))

Max Activating Token Index: 317