Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6016 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1581264 (Python Code)

Max Activating Token Index: 814

Text #1

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1466535 (Python Code)

Max Activating Token Index: 685

Text #2

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1558124 (Python Code)

Max Activating Token Index: 570

Text #3

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1619177 (Python Code)

Max Activating Token Index: 751

Text #4

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1548169 (Python Code)

Max Activating Token Index: 474

Text #5

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0687. Min Act: -0.0000

Data Index: 1466650 (Python Code)

Max Activating Token Index: 216

Text #6

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1601922 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1645455 (Python Code)

Max Activating Token Index: 844

Text #8

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1379806 (Python Code)

Max Activating Token Index: 691

Text #9

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1369834 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1546374 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1563869 (Python Code)

Max Activating Token Index: 463

Text #12

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1379844 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1368050 (Python Code)

Max Activating Token Index: 97

Text #14

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1627626 (Python Code)

Max Activating Token Index: 103

Text #15

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1554189 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1532751 (Python Code)

Max Activating Token Index: 936

Text #17

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1570620 (Python Code)

Max Activating Token Index: 381

Text #18

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1530253 (Python Code)

Max Activating Token Index: 583

Text #19

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1396898 (Python Code)

Max Activating Token Index: 484