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

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

Neuron 121 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: 0.4720. Min Range: -0.4720

Max Act: 0.4633. Min Act: -0.0003

Data Index: 1396285 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4720. Min Act: -0.0002

Data Index: 1643353 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4583. Min Act: -0.0003

Data Index: 1440106 (Python Code)

Max Activating Token Index: 181

Text #3

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4420. Min Act: -0.0002

Data Index: 1447631 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4425. Min Act: -0.0002

Data Index: 1481483 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4288. Min Act: -0.0003

Data Index: 1611834 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4397. Min Act: -0.0002

Data Index: 1415109 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4312. Min Act: -0.0002

Data Index: 1639464 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4258. Min Act: -0.0002

Data Index: 1599315 (Python Code)

Max Activating Token Index: 288

Text #9

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4139. Min Act: -0.0002

Data Index: 1586723 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4276. Min Act: -0.0002

Data Index: 1506304 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4239. Min Act: -0.0002

Data Index: 1447489 (Python Code)

Max Activating Token Index: 181

Text #12

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4235. Min Act: -0.0002

Data Index: 1590711 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4259. Min Act: -0.0002

Data Index: 1528401 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4047. Min Act: -0.0002

Data Index: 1523149 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4053. Min Act: -0.0002

Data Index: 1581073 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4094. Min Act: -0.0003

Data Index: 1535824 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4053. Min Act: -0.0002

Data Index: 1540435 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4214. Min Act: -0.0002

Data Index: 1572907 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4076. Min Act: -0.0002

Data Index: 1606388 (Python Code)

Max Activating Token Index: 352