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

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

Neuron 4252 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1504928 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.6821. Min Act: -0.0001

Data Index: 1396736 (Python Code)

Max Activating Token Index: 573

Text #2

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5974. Min Act: -0.0001

Data Index: 1647869 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5788. Min Act: -0.0001

Data Index: 1368512 (Python Code)

Max Activating Token Index: 478

Text #4

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5383. Min Act: -0.0001

Data Index: 1585145 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5482. Min Act: -0.0001

Data Index: 1604594 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1597639 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5623. Min Act: -0.0001

Data Index: 1559169 (Python Code)

Max Activating Token Index: 97

Text #8

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1385343 (Python Code)

Max Activating Token Index: 472

Text #9

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5419. Min Act: -0.0001

Data Index: 1509566 (Python Code)

Max Activating Token Index: 1006

Text #10

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5555. Min Act: -0.0001

Data Index: 1416461 (Python Code)

Max Activating Token Index: 531

Text #11

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.4928. Min Act: -0.0001

Data Index: 1479281 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5636. Min Act: -0.0001

Data Index: 1641848 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5623. Min Act: -0.0001

Data Index: 1427526 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5267. Min Act: -0.0001

Data Index: 1570292 (Python Code)

Max Activating Token Index: 432

Text #15

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5426. Min Act: -0.0001

Data Index: 1404700 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.4863. Min Act: -0.0001

Data Index: 1546299 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1385590 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5366. Min Act: -0.0001

Data Index: 1553968 (Python Code)

Max Activating Token Index: 89

Text #19

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5160. Min Act: -0.0001

Data Index: 1361820 (Python Code)

Max Activating Token Index: 980