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

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

Neuron 4263 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3123. Min Range: -1.3123

Max Act: 1.3123. Min Act: -0.0002

Data Index: 1575911 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 1.3123. Min Range: -1.3123

Max Act: 1.2297. Min Act: -0.0002

Data Index: 1512253 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 1.3123. Min Range: -1.3123

Max Act: 1.0484. Min Act: -0.0002

Data Index: 1397831 (Python Code)

Max Activating Token Index: 128

Text #3

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.9716. Min Act: -0.0002

Data Index: 1516630 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.9737. Min Act: -0.0002

Data Index: 1564067 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.9347. Min Act: -0.0002

Data Index: 1366959 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.8894. Min Act: -0.0002

Data Index: 1510882 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.9469. Min Act: -0.0002

Data Index: 1368735 (Python Code)

Max Activating Token Index: 265

Text #8

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.9510. Min Act: -0.0002

Data Index: 1627326 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.9368. Min Act: -0.0002

Data Index: 1384280 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.8518. Min Act: -0.0002

Data Index: 1479192 (Python Code)

Max Activating Token Index: 582

Text #11

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.9299. Min Act: -0.0002

Data Index: 1488785 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.8832. Min Act: -0.0002

Data Index: 1601109 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.8267. Min Act: -0.0002

Data Index: 1468578 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.8484. Min Act: -0.0002

Data Index: 1608642 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.8376. Min Act: -0.0002

Data Index: 1624563 (Python Code)

Max Activating Token Index: 348

Text #16

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.8399. Min Act: -0.0002

Data Index: 1515856 (Python Code)

Max Activating Token Index: 881

Text #17

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.7854. Min Act: -0.0002

Data Index: 1563951 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.8431. Min Act: -0.0002

Data Index: 1590837 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 1.3123. Min Range: -1.3123

Max Act: 0.7658. Min Act: -0.0002

Data Index: 1601338 (Python Code)

Max Activating Token Index: 139