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

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

Neuron 4341 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: 0.7022. Min Range: -0.7022

Max Act: 0.7022. Min Act: -0.0002

Data Index: 1477007 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5890. Min Act: -0.0002

Data Index: 1487834 (Python Code)

Max Activating Token Index: 281

Text #2

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5811. Min Act: -0.0002

Data Index: 1600460 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5855. Min Act: -0.0002

Data Index: 1557049 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5619. Min Act: -0.0002

Data Index: 1581747 (Python Code)

Max Activating Token Index: 328

Text #5

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5760. Min Act: -0.0002

Data Index: 1436698 (Python Code)

Max Activating Token Index: 228

Text #6

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5825. Min Act: -0.0003

Data Index: 1522264 (Python Code)

Max Activating Token Index: 432

Text #7

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5391. Min Act: -0.0002

Data Index: 1407075 (Python Code)

Max Activating Token Index: 214

Text #8

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5880. Min Act: -0.0002

Data Index: 1600976 (Python Code)

Max Activating Token Index: 311

Text #9

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5742. Min Act: -0.0002

Data Index: 1607272 (Python Code)

Max Activating Token Index: 265

Text #10

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5742. Min Act: -0.0002

Data Index: 1484043 (Python Code)

Max Activating Token Index: 265

Text #11

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5480. Min Act: -0.0002

Data Index: 1500041 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5680. Min Act: -0.0002

Data Index: 1416042 (Python Code)

Max Activating Token Index: 756

Text #13

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5911. Min Act: -0.0002

Data Index: 1604544 (Python Code)

Max Activating Token Index: 342

Text #14

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5863. Min Act: -0.0002

Data Index: 1498999 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5441. Min Act: -0.0002

Data Index: 1488627 (Python Code)

Max Activating Token Index: 559

Text #16

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5610. Min Act: -0.0002

Data Index: 1648193 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5352. Min Act: -0.0002

Data Index: 1577357 (Python Code)

Max Activating Token Index: 341

Text #18

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5490. Min Act: -0.0002

Data Index: 1619792 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5299. Min Act: -0.0002

Data Index: 1476435 (Python Code)

Max Activating Token Index: 350