Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1843 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0023. Min Act: -0.0006

Data Index: 28044 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0022. Min Act: -0.0006

Data Index: 156859 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0022. Min Act: -0.0006

Data Index: 1013697 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0006

Data Index: 1249729 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0006

Data Index: 1261784 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0006

Data Index: 239482 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0006

Data Index: 783472 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0006

Data Index: 1185578 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0006

Data Index: 819018 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0006

Data Index: 54849 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1312233 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0006

Data Index: 579216 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0006

Data Index: 379120 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0006

Data Index: 112930 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0006

Data Index: 512717 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0006

Data Index: 435058 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0006

Data Index: 309236 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0006

Data Index: 300729 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1222914 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0006

Data Index: 661377 (C4 (Web Text))

Max Activating Token Index: 309