Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 944 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1130. Min Act: -0.0006

Data Index: 1209018 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1120. Min Act: -0.0006

Data Index: 368954 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1102. Min Act: -0.0006

Data Index: 1114401 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1073. Min Act: -0.0006

Data Index: 906774 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1040. Min Act: -0.0006

Data Index: 576467 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1050. Min Act: -0.0006

Data Index: 377916 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1043. Min Act: -0.0006

Data Index: 649423 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1020. Min Act: -0.0006

Data Index: 697361 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1036. Min Act: -0.0006

Data Index: 860614 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1030. Min Act: -0.0006

Data Index: 16991 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1028. Min Act: -0.0006

Data Index: 43605 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1025. Min Act: -0.0006

Data Index: 1198929 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1044. Min Act: -0.0006

Data Index: 646247 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1022. Min Act: -0.0006

Data Index: 1251134 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1020. Min Act: -0.0006

Data Index: 1267648 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1019. Min Act: -0.0006

Data Index: 102611 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1018. Min Act: -0.0006

Data Index: 1260863 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0994. Min Act: -0.0006

Data Index: 969197 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1032. Min Act: -0.0006

Data Index: 759365 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1011. Min Act: -0.0006

Data Index: 195016 (C4 (Web Text))

Max Activating Token Index: 753