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

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

Neuron 1523 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: 2.0948. Min Range: -2.0948

Max Act: 2.0948. Min Act: -0.0000

Data Index: 830743 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.8917. Min Act: -0.0000

Data Index: 647621 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.6859. Min Act: -0.0000

Data Index: 311779 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.6759. Min Act: -0.0000

Data Index: 234963 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.4033. Min Act: -0.0000

Data Index: 252249 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1242773 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.4980. Min Act: -0.0000

Data Index: 916889 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.3801. Min Act: -0.0000

Data Index: 259876 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.3815. Min Act: -0.0000

Data Index: 60314 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.4393. Min Act: -0.0000

Data Index: 639789 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.3561. Min Act: -0.0000

Data Index: 911278 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.4209. Min Act: -0.0000

Data Index: 122444 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.4096. Min Act: -0.0000

Data Index: 307350 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.4199. Min Act: -0.0000

Data Index: 237638 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.3942. Min Act: -0.0000

Data Index: 123874 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.4076. Min Act: -0.0000

Data Index: 21734 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.3004. Min Act: -0.0000

Data Index: 364395 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.4676. Min Act: -0.0000

Data Index: 96098 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.3045. Min Act: -0.0000

Data Index: 364900 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.2801. Min Act: -0.0000

Data Index: 863371 (C4 (Web Text))

Max Activating Token Index: 704