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

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

Neuron 4527 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1262267 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0105. Min Act: -0.0002

Data Index: 601306 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0102. Min Act: -0.0002

Data Index: 882210 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 415874 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 337012 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1281699 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0096. Min Act: -0.0002

Data Index: 634974 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0096. Min Act: -0.0002

Data Index: 880232 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0096. Min Act: -0.0002

Data Index: 327609 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1203802 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0002

Data Index: 826146 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1229382 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1250801 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1321623 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0002

Data Index: 423375 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1138102 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0091. Min Act: -0.0002

Data Index: 364649 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0091. Min Act: -0.0002

Data Index: 613837 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1112352 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0091. Min Act: -0.0002

Data Index: 68737 (C4 (Web Text))

Max Activating Token Index: 77