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

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

Neuron 1384 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0001

Data Index: 940624 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1081. Min Act: -0.0001

Data Index: 201617 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0985. Min Act: -0.0001

Data Index: 290076 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0915. Min Act: -0.0001

Data Index: 684266 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0884. Min Act: -0.0000

Data Index: 759687 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1051. Min Act: -0.0001

Data Index: 173844 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0902. Min Act: -0.0001

Data Index: 721260 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0910. Min Act: -0.0000

Data Index: 519238 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0939. Min Act: -0.0001

Data Index: 200269 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1023214 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0895. Min Act: -0.0001

Data Index: 665497 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0885. Min Act: -0.0001

Data Index: 385339 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1325242 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0844. Min Act: -0.0001

Data Index: 816415 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0830. Min Act: -0.0001

Data Index: 36063 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0860. Min Act: -0.0000

Data Index: 887770 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0852. Min Act: -0.0001

Data Index: 20901 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0786. Min Act: -0.0001

Data Index: 987491 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0869. Min Act: -0.0001

Data Index: 203693 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1013554 (C4 (Web Text))

Max Activating Token Index: 49