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

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

Neuron 4843 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: 2.8167. Min Range: -2.8167

Max Act: 2.8167. Min Act: -0.0000

Data Index: 1439838 (Python Code)

Max Activating Token Index: 86

Text #1

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.7907. Min Act: -0.0000

Data Index: 1657015 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.5456. Min Act: -0.0000

Data Index: 1473601 (Python Code)

Max Activating Token Index: 291

Text #3

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.1496. Min Act: -0.0000

Data Index: 1426484 (Python Code)

Max Activating Token Index: 160

Text #4

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.2547. Min Act: -0.0000

Data Index: 1627660 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.2315. Min Act: -0.0000

Data Index: 1634838 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.1061. Min Act: -0.0000

Data Index: 1392259 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.9782. Min Act: -0.0000

Data Index: 1629784 (Python Code)

Max Activating Token Index: 561

Text #8

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.0769. Min Act: -0.0000

Data Index: 1503641 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.1656. Min Act: -0.0001

Data Index: 1647975 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.0509. Min Act: -0.0000

Data Index: 1656120 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.1342. Min Act: -0.0000

Data Index: 1471230 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.1003. Min Act: -0.0000

Data Index: 1417163 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.0012. Min Act: -0.0000

Data Index: 1609351 (Python Code)

Max Activating Token Index: 311

Text #14

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.9842. Min Act: -0.0000

Data Index: 1496669 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.9728. Min Act: -0.0000

Data Index: 1433839 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.9539. Min Act: -0.0000

Data Index: 1446817 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.0313. Min Act: -0.0000

Data Index: 1596026 (Python Code)

Max Activating Token Index: 457

Text #18

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.7179. Min Act: -0.0000

Data Index: 1599468 (Python Code)

Max Activating Token Index: 258

Text #19

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.7292. Min Act: -0.0000

Data Index: 1410961 (Python Code)

Max Activating Token Index: 827