Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1746 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1380. Min Act: -0.0001

Data Index: 87976 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1478491 (Python Code)

Max Activating Token Index: 651

Text #2

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1071. Min Act: -0.0000

Data Index: 265913 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1329771 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1077. Min Act: -0.0000

Data Index: 396055 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1579069 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1113. Min Act: -0.0000

Data Index: 231500 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1035. Min Act: -0.0000

Data Index: 692625 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1095876 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1163818 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1005. Min Act: -0.0001

Data Index: 722627 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1000. Min Act: -0.0000

Data Index: 433019 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1001. Min Act: -0.0000

Data Index: 988775 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1589106 (Python Code)

Max Activating Token Index: 996

Text #14

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1001. Min Act: -0.0001

Data Index: 718109 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1268572 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1127133 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1506573 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1014479 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1589658 (Python Code)

Max Activating Token Index: 632