Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4840 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1054895 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.6017. Min Act: -0.0000

Data Index: 846539 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5045. Min Act: -0.0000

Data Index: 592265 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5158. Min Act: -0.0000

Data Index: 912742 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5094. Min Act: -0.0000

Data Index: 108602 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5272. Min Act: -0.0000

Data Index: 894197 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5323. Min Act: -0.0000

Data Index: 600043 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4994. Min Act: -0.0000

Data Index: 923205 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5234. Min Act: -0.0000

Data Index: 851096 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4832. Min Act: -0.0000

Data Index: 660764 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5246. Min Act: -0.0000

Data Index: 612728 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4948. Min Act: -0.0000

Data Index: 841062 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4853. Min Act: -0.0000

Data Index: 612872 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4881. Min Act: -0.0000

Data Index: 479163 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4837. Min Act: -0.0000

Data Index: 43744 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1175431 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1292982 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4806. Min Act: -0.0000

Data Index: 761513 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5088. Min Act: -0.0000

Data Index: 340114 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4873. Min Act: -0.0000

Data Index: 802121 (C4 (Web Text))

Max Activating Token Index: 95