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

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

Neuron 1902 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.8484. Min Act: -0.0000

Data Index: 1491308 (Python Code)

Max Activating Token Index: 305

Text #1

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.7520. Min Act: -0.0000

Data Index: 1532108 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.5354. Min Act: -0.0000

Data Index: 1378792 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.4288. Min Act: -0.0000

Data Index: 1573008 (Python Code)

Max Activating Token Index: 595

Text #4

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.2340. Min Act: -0.0000

Data Index: 1646057 (Python Code)

Max Activating Token Index: 428

Text #5

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.2111. Min Act: -0.0000

Data Index: 1644120 (Python Code)

Max Activating Token Index: 489

Text #6

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.1691. Min Act: -0.0000

Data Index: 1394530 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.2131. Min Act: -0.0000

Data Index: 1426598 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.2041. Min Act: -0.0000

Data Index: 1442794 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.2094. Min Act: -0.0000

Data Index: 1401157 (Python Code)

Max Activating Token Index: 500

Text #10

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.2211. Min Act: -0.0000

Data Index: 189114 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.0835. Min Act: -0.0000

Data Index: 1445251 (Python Code)

Max Activating Token Index: 796

Text #12

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.0801. Min Act: -0.0000

Data Index: 1631387 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.0623. Min Act: -0.0000

Data Index: 1605798 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.0243. Min Act: -0.0000

Data Index: 1390833 (Python Code)

Max Activating Token Index: 672

Text #15

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.1017. Min Act: -0.0000

Data Index: 1373127 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.0966. Min Act: -0.0000

Data Index: 1585300 (Python Code)

Max Activating Token Index: 118

Text #17

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.0726. Min Act: -0.0000

Data Index: 1361156 (Python Code)

Max Activating Token Index: 203

Text #18

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.1433. Min Act: -0.0000

Data Index: 1428502 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 2.8484. Min Range: -2.8484

Max Act: 2.0557. Min Act: -0.0000

Data Index: 1501789 (Python Code)

Max Activating Token Index: 348