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

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

Neuron 3805 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.8180. Min Act: -0.0002

Data Index: 494011 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7971. Min Act: -0.0002

Data Index: 1089640 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7301. Min Act: -0.0002

Data Index: 1117930 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7533. Min Act: -0.0002

Data Index: 733915 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7852. Min Act: -0.0002

Data Index: 885398 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7137. Min Act: -0.0002

Data Index: 6230 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7066. Min Act: -0.0002

Data Index: 696620 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6801. Min Act: -0.0002

Data Index: 1022745 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7380. Min Act: -0.0002

Data Index: 929893 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6646. Min Act: -0.0002

Data Index: 191276 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7136. Min Act: -0.0002

Data Index: 1017949 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6878. Min Act: -0.0002

Data Index: 938529 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5569. Min Act: -0.0002

Data Index: 178588 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6801. Min Act: -0.0002

Data Index: 1165862 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6339. Min Act: -0.0002

Data Index: 509787 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6772. Min Act: -0.0002

Data Index: 883410 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6505. Min Act: -0.0002

Data Index: 1264561 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6140. Min Act: -0.0002

Data Index: 451721 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6465. Min Act: -0.0002

Data Index: 343685 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6875. Min Act: -0.0002

Data Index: 248713 (C4 (Web Text))

Max Activating Token Index: 385