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

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

Neuron 4901 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: 1.4057. Min Range: -1.4057

Max Act: 1.4057. Min Act: -0.0000

Data Index: 56638 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.1214. Min Act: -0.0000

Data Index: 712377 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.0868. Min Act: -0.0000

Data Index: 127030 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1331199 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1285763 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.9663. Min Act: -0.0000

Data Index: 653854 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.9840. Min Act: -0.0000

Data Index: 119118 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.9393. Min Act: -0.0000

Data Index: 697514 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.9376. Min Act: -0.0000

Data Index: 375131 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1150807 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.9231. Min Act: -0.0000

Data Index: 465552 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1081941 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.8753. Min Act: -0.0000

Data Index: 244250 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.9011. Min Act: -0.0000

Data Index: 669762 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.8540. Min Act: -0.0000

Data Index: 534767 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1059393 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1051533 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.8441. Min Act: -0.0000

Data Index: 280527 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.8554. Min Act: -0.0000

Data Index: 742210 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 1.4057. Min Range: -1.4057

Max Act: 0.8487. Min Act: -0.0000

Data Index: 527870 (C4 (Web Text))

Max Activating Token Index: 1022