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

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

Neuron 5800 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.6176. Min Act: -0.0000

Data Index: 439892 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.6128. Min Act: -0.0000

Data Index: 965770 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5135. Min Act: -0.0000

Data Index: 949998 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5444. Min Act: -0.0000

Data Index: 952297 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5067. Min Act: -0.0000

Data Index: 624950 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1308043 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5665. Min Act: -0.0000

Data Index: 30747 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5257. Min Act: -0.0000

Data Index: 425724 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5251. Min Act: -0.0000

Data Index: 36928 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5073. Min Act: -0.0000

Data Index: 628965 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1061512 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4966. Min Act: -0.0000

Data Index: 278010 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1040086 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4945. Min Act: -0.0000

Data Index: 481741 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5126. Min Act: -0.0000

Data Index: 235817 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5280. Min Act: -0.0000

Data Index: 836455 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5250. Min Act: -0.0000

Data Index: 168222 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5081. Min Act: -0.0000

Data Index: 260409 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4873. Min Act: -0.0000

Data Index: 578391 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1556276 (Python Code)

Max Activating Token Index: 291