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

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

Neuron 388 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.8307. Min Act: -0.0000

Data Index: 706697 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5839. Min Act: -0.0000

Data Index: 66132 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5146. Min Act: -0.0000

Data Index: 725063 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4875. Min Act: -0.0000

Data Index: 478811 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5112. Min Act: -0.0000

Data Index: 612436 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4953. Min Act: -0.0000

Data Index: 927075 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5191. Min Act: -0.0000

Data Index: 125854 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4827. Min Act: -0.0000

Data Index: 831931 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5146. Min Act: -0.0000

Data Index: 661398 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4886. Min Act: -0.0000

Data Index: 535434 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4884. Min Act: -0.0000

Data Index: 768131 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1210136 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4690. Min Act: -0.0000

Data Index: 937055 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4643. Min Act: -0.0000

Data Index: 301540 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4853. Min Act: -0.0000

Data Index: 273235 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4359. Min Act: -0.0000

Data Index: 618631 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4505. Min Act: -0.0000

Data Index: 68842 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4333. Min Act: -0.0000

Data Index: 231299 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4462. Min Act: -0.0000

Data Index: 599602 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1113758 (C4 (Web Text))

Max Activating Token Index: 808