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

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

Neuron 1233 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1558. Min Range: -2.1558

Max Act: 2.0692. Min Act: -0.0000

Data Index: 604520 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 2.1558. Min Range: -2.1558

Max Act: 2.1476. Min Act: -0.0000

Data Index: 680474 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 2.1558. Min Range: -2.1558

Max Act: 2.1188. Min Act: -0.0000

Data Index: 1147313 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 2.1558. Min Range: -2.1558

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1312254 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.9838. Min Act: -0.0000

Data Index: 668971 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 2.1558. Min Range: -2.1558

Max Act: 2.0440. Min Act: -0.0000

Data Index: 322003 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 2.1558. Min Range: -2.1558

Max Act: 2.1558. Min Act: -0.0000

Data Index: 1139011 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.8986. Min Act: -0.0000

Data Index: 107400 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.9633. Min Act: -0.0000

Data Index: 74441 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.9030. Min Act: -0.0000

Data Index: 1280998 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 2.1558. Min Range: -2.1558

Max Act: 2.0131. Min Act: -0.0000

Data Index: 843488 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.8828. Min Act: -0.0000

Data Index: 1049431 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.8770. Min Act: -0.0000

Data Index: 26068 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.8593. Min Act: -0.0000

Data Index: 904024 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.8498. Min Act: -0.0000

Data Index: 386694 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.8360. Min Act: -0.0000

Data Index: 424631 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.6436. Min Act: -0.0000

Data Index: 979881 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.7770. Min Act: -0.0000

Data Index: 594641 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.6780. Min Act: -0.0000

Data Index: 867048 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 2.1558. Min Range: -2.1558

Max Act: 1.6725. Min Act: -0.0000

Data Index: 29350 (C4 (Web Text))

Max Activating Token Index: 634