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

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

Neuron 4937 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1736. Min Act: -0.0000

Data Index: 14428 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1571. Min Act: -0.0000

Data Index: 65446 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1522. Min Act: -0.0000

Data Index: 895528 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1204625 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1126. Min Act: -0.0000

Data Index: 838873 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1149. Min Act: -0.0000

Data Index: 689156 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1099. Min Act: -0.0000

Data Index: 190187 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1144115 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1132. Min Act: -0.0000

Data Index: 873105 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1089. Min Act: -0.0000

Data Index: 745586 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1068. Min Act: -0.0000

Data Index: 987849 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1028. Min Act: -0.0000

Data Index: 505539 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1054. Min Act: -0.0000

Data Index: 644847 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1016. Min Act: -0.0000

Data Index: 966875 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1130182 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1031. Min Act: -0.0000

Data Index: 196837 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1023. Min Act: -0.0000

Data Index: 392698 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1005936 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.0978. Min Act: -0.0000

Data Index: 424895 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1054. Min Act: -0.0000

Data Index: 319849 (C4 (Web Text))

Max Activating Token Index: 83