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

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

Neuron 5420 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: 0.1109. Min Range: -0.1109

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1318875 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1077. Min Act: -0.0001

Data Index: 565849 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0880. Min Act: -0.0001

Data Index: 302305 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0998. Min Act: -0.0001

Data Index: 367694 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0955. Min Act: -0.0001

Data Index: 165818 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1271592 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0787. Min Act: -0.0001

Data Index: 329936 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0930. Min Act: -0.0001

Data Index: 483598 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1068. Min Act: -0.0001

Data Index: 810508 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0900. Min Act: -0.0001

Data Index: 628776 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0001

Data Index: 196159 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1314098 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0883. Min Act: -0.0001

Data Index: 358642 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1172178 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0932. Min Act: -0.0001

Data Index: 848266 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1098453 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0841. Min Act: -0.0001

Data Index: 926762 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0704. Min Act: -0.0001

Data Index: 622158 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0811. Min Act: -0.0001

Data Index: 644916 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1080209 (C4 (Web Text))

Max Activating Token Index: 361