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

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

Neuron 4971 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: 0.6165. Min Range: -0.6165

Max Act: 0.6001. Min Act: -0.0000

Data Index: 956884 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.6165. Min Act: -0.0000

Data Index: 653783 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.5888. Min Act: 0.0000

Data Index: 992977 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1267425 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.5822. Min Act: -0.0000

Data Index: 502220 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1257003 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.5042. Min Act: -0.0000

Data Index: 553509 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.5016. Min Act: -0.0000

Data Index: 336168 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.5074. Min Act: 0.0000

Data Index: 472696 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1011780 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4634. Min Act: 0.0000

Data Index: 873028 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4638. Min Act: -0.0000

Data Index: 598102 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4635. Min Act: -0.0000

Data Index: 839958 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4210. Min Act: -0.0000

Data Index: 634045 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4657. Min Act: 0.0000

Data Index: 398403 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1013594 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1042996 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4248. Min Act: -0.0000

Data Index: 269545 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4153. Min Act: -0.0000

Data Index: 321943 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4372. Min Act: 0.0000

Data Index: 999025 (C4 (Web Text))

Max Activating Token Index: 79