Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1393 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7754. Min Act: -0.0001

Data Index: 487421 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7750. Min Act: -0.0002

Data Index: 679994 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.8159. Min Act: -0.0001

Data Index: 872089 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7224. Min Act: -0.0001

Data Index: 1230049 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7220. Min Act: -0.0002

Data Index: 1042079 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6934. Min Act: -0.0002

Data Index: 617085 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7165. Min Act: -0.0002

Data Index: 1099750 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7110. Min Act: -0.0002

Data Index: 1086153 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7033. Min Act: -0.0002

Data Index: 61019 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6585. Min Act: -0.0002

Data Index: 739344 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6776. Min Act: -0.0001

Data Index: 414287 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7038. Min Act: -0.0001

Data Index: 628435 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6777. Min Act: -0.0001

Data Index: 591913 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6925. Min Act: -0.0001

Data Index: 977787 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7037. Min Act: -0.0002

Data Index: 189710 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6829. Min Act: -0.0001

Data Index: 1186323 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6678. Min Act: -0.0001

Data Index: 327097 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6772. Min Act: -0.0002

Data Index: 1318869 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6495. Min Act: -0.0001

Data Index: 306552 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6641. Min Act: -0.0001

Data Index: 806596 (C4 (Web Text))

Max Activating Token Index: 362