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

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

Neuron 966 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1626354 (Python Code)

Max Activating Token Index: 251

Text #1

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1586452 (Python Code)

Max Activating Token Index: 584

Text #2

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1459446 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3800. Min Act: -0.0000

Data Index: 1535376 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1377296 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1419926 (Python Code)

Max Activating Token Index: 213

Text #6

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1431051 (Python Code)

Max Activating Token Index: 958

Text #7

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3013. Min Act: -0.0000

Data Index: 1593296 (Python Code)

Max Activating Token Index: 353

Text #8

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1403854 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2817. Min Act: -0.0000

Data Index: 1625477 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1460979 (Python Code)

Max Activating Token Index: 344

Text #11

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1472. Min Act: -0.0000

Data Index: 1558676 (Python Code)

Max Activating Token Index: 401

Text #12

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1634265 (Python Code)

Max Activating Token Index: 302

Text #13

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1480865 (Python Code)

Max Activating Token Index: 417

Text #14

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1654283 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1577490 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1524122 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1608335 (Python Code)

Max Activating Token Index: 733

Text #18

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1411640 (Python Code)

Max Activating Token Index: 276

Text #19

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1471587 (Python Code)

Max Activating Token Index: 330