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

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

Neuron 1990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.9111. Min Act: -0.0000

Data Index: 245586 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1100422 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8472. Min Act: -0.0000

Data Index: 882237 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8132. Min Act: -0.0000

Data Index: 762838 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7980. Min Act: -0.0000

Data Index: 560075 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7201. Min Act: -0.0000

Data Index: 942296 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7900. Min Act: -0.0000

Data Index: 513226 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6995. Min Act: -0.0000

Data Index: 607677 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1272341 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6647. Min Act: -0.0000

Data Index: 285922 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1257819 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7119. Min Act: -0.0000

Data Index: 746082 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6311. Min Act: -0.0000

Data Index: 235157 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.5913. Min Act: -0.0000

Data Index: 629041 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.5814. Min Act: -0.0000

Data Index: 230930 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6427. Min Act: -0.0000

Data Index: 720728 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1220460 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6763. Min Act: -0.0000

Data Index: 276564 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1117579 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1225951 (C4 (Web Text))

Max Activating Token Index: 255