Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3049 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.8287. Min Act: -0.0004

Data Index: 1568733 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.8069. Min Act: -0.0004

Data Index: 1609346 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6214. Min Act: -0.0004

Data Index: 1542738 (Python Code)

Max Activating Token Index: 583

Text #3

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.8214. Min Act: -0.0004

Data Index: 1580845 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6047. Min Act: -0.0004

Data Index: 1474504 (Python Code)

Max Activating Token Index: 540

Text #5

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.8207. Min Act: -0.0004

Data Index: 1623620 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6553. Min Act: -0.0004

Data Index: 1443015 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5226. Min Act: -0.0004

Data Index: 1632505 (Python Code)

Max Activating Token Index: 863

Text #8

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6225. Min Act: -0.0004

Data Index: 1418848 (Python Code)

Max Activating Token Index: 455

Text #9

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6609. Min Act: -0.0004

Data Index: 1447159 (Python Code)

Max Activating Token Index: 437

Text #10

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.4520. Min Act: -0.0004

Data Index: 1404070 (Python Code)

Max Activating Token Index: 300

Text #11

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5492. Min Act: -0.0004

Data Index: 1610696 (Python Code)

Max Activating Token Index: 869

Text #12

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5825. Min Act: -0.0004

Data Index: 1370138 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5827. Min Act: -0.0004

Data Index: 1530422 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.4008. Min Act: -0.0004

Data Index: 1465167 (Python Code)

Max Activating Token Index: 1003

Text #15

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5984. Min Act: -0.0004

Data Index: 1651501 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5186. Min Act: -0.0004

Data Index: 1504444 (Python Code)

Max Activating Token Index: 331

Text #17

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5522. Min Act: -0.0004

Data Index: 1509719 (Python Code)

Max Activating Token Index: 828

Text #18

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5492. Min Act: -0.0004

Data Index: 1581665 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.4815. Min Act: -0.0004

Data Index: 1588976 (Python Code)

Max Activating Token Index: 873