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

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

Neuron 4346 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.6834. Min Act: -0.0001

Data Index: 11512 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2908. Min Act: -0.0001

Data Index: 378673 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.3675. Min Act: -0.0001

Data Index: 251243 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2517. Min Act: -0.0001

Data Index: 717370 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2905. Min Act: -0.0001

Data Index: 977764 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2983. Min Act: -0.0001

Data Index: 1331041 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2864. Min Act: -0.0001

Data Index: 17351 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2523. Min Act: -0.0001

Data Index: 1149185 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2776. Min Act: -0.0001

Data Index: 1253830 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2538. Min Act: -0.0001

Data Index: 720071 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2988. Min Act: -0.0001

Data Index: 475613 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2331. Min Act: -0.0001

Data Index: 461585 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2241. Min Act: -0.0001

Data Index: 592698 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2372. Min Act: -0.0001

Data Index: 1115381 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2942. Min Act: -0.0001

Data Index: 956846 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2292. Min Act: -0.0001

Data Index: 813837 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.1884. Min Act: -0.0001

Data Index: 1175323 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2581. Min Act: -0.0001

Data Index: 941596 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2021. Min Act: -0.0001

Data Index: 358039 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2389. Min Act: -0.0001

Data Index: 289548 (C4 (Web Text))

Max Activating Token Index: 394