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

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

Neuron 4442 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: -0.0002

Data Index: 27844 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0545. Min Act: -0.0002

Data Index: 984780 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0491. Min Act: -0.0002

Data Index: 969935 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1101347 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0460. Min Act: -0.0002

Data Index: 794989 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0429. Min Act: -0.0003

Data Index: 942319 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0445. Min Act: -0.0002

Data Index: 444401 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0437. Min Act: -0.0002

Data Index: 382314 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0430. Min Act: -0.0002

Data Index: 901651 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1304926 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0395. Min Act: -0.0002

Data Index: 138463 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0392. Min Act: -0.0002

Data Index: 151125 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0402. Min Act: -0.0003

Data Index: 716236 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0389. Min Act: -0.0002

Data Index: 28278 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0392. Min Act: -0.0002

Data Index: 947180 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0401. Min Act: -0.0003

Data Index: 311475 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0396. Min Act: -0.0002

Data Index: 764255 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0404. Min Act: -0.0003

Data Index: 722683 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0397. Min Act: -0.0003

Data Index: 813950 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0395. Min Act: -0.0002

Data Index: 737443 (C4 (Web Text))

Max Activating Token Index: 565