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

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

Neuron 3159 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1545058 (Python Code)

Max Activating Token Index: 896

Text #1

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1636447 (Python Code)

Max Activating Token Index: 609

Text #2

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1359910 (Python Code)

Max Activating Token Index: 477

Text #3

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1447662 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1488844 (Python Code)

Max Activating Token Index: 601

Text #5

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1585146 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1397401 (Python Code)

Max Activating Token Index: 318

Text #7

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1564125 (Python Code)

Max Activating Token Index: 871

Text #8

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1583. Min Act: -0.0000

Data Index: 1539653 (Python Code)

Max Activating Token Index: 359

Text #9

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1413076 (Python Code)

Max Activating Token Index: 900

Text #10

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1648471 (Python Code)

Max Activating Token Index: 169

Text #11

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1493113 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1519666 (Python Code)

Max Activating Token Index: 732

Text #13

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1446871 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1379847 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1500331 (Python Code)

Max Activating Token Index: 1010

Text #16

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1504469 (Python Code)

Max Activating Token Index: 194

Text #17

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1441598 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1396913 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1494735 (Python Code)

Max Activating Token Index: 854