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

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

Neuron 4740 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: 1.8085. Min Range: -1.8085

Max Act: 1.8085. Min Act: -0.0000

Data Index: 392389 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.6825. Min Act: -0.0000

Data Index: 156544 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.5660. Min Act: -0.0000

Data Index: 174852 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.5566. Min Act: -0.0000

Data Index: 542735 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1263759 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.6889. Min Act: -0.0000

Data Index: 661466 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.4928. Min Act: -0.0000

Data Index: 249376 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.6492. Min Act: -0.0000

Data Index: 89268 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.5598. Min Act: -0.0000

Data Index: 1264194 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.4657. Min Act: -0.0000

Data Index: 707960 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.3609. Min Act: -0.0000

Data Index: 421174 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.3047. Min Act: -0.0000

Data Index: 209005 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.3283. Min Act: -0.0000

Data Index: 238649 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.1916. Min Act: -0.0000

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.3151. Min Act: -0.0000

Data Index: 1283868 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.3179. Min Act: -0.0000

Data Index: 255395 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1135379 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.3010. Min Act: -0.0000

Data Index: 352208 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.2938. Min Act: -0.0000

Data Index: 345058 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 1.8085. Min Range: -1.8085

Max Act: 1.3258. Min Act: -0.0000

Data Index: 487783 (C4 (Web Text))

Max Activating Token Index: 399