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

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

Neuron 3570 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: 0.5869. Min Range: -0.5869

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1150692 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.5533. Min Act: -0.0000

Data Index: 917051 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.5642. Min Act: -0.0000

Data Index: 955317 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4982. Min Act: -0.0000

Data Index: 636846 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4971. Min Act: -0.0000

Data Index: 897729 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1288744 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.5218. Min Act: -0.0000

Data Index: 878939 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4850. Min Act: -0.0000

Data Index: 897193 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1242756 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4965. Min Act: -0.0000

Data Index: 208191 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.5118. Min Act: -0.0000

Data Index: 206878 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4959. Min Act: -0.0000

Data Index: 918204 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.5056. Min Act: -0.0000

Data Index: 489178 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.5043. Min Act: -0.0000

Data Index: 680446 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1103623 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4714. Min Act: -0.0000

Data Index: 679527 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4692. Min Act: -0.0000

Data Index: 761876 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4995. Min Act: -0.0000

Data Index: 303725 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1171325 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1227300 (C4 (Web Text))

Max Activating Token Index: 320