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

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

Neuron 4475 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: 2.8270. Min Range: -2.8270

Max Act: 2.8270. Min Act: -0.0000

Data Index: 1409708 (Python Code)

Max Activating Token Index: 530

Text #1

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.6791. Min Act: -0.0000

Data Index: 1497845 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.2240. Min Act: -0.0000

Data Index: 1406357 (Python Code)

Max Activating Token Index: 460

Text #3

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.2766. Min Act: -0.0000

Data Index: 1627082 (Python Code)

Max Activating Token Index: 207

Text #4

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.3123. Min Act: -0.0000

Data Index: 1602601 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.2664. Min Act: -0.0000

Data Index: 1366899 (Python Code)

Max Activating Token Index: 738

Text #6

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.1211. Min Act: -0.0000

Data Index: 1476541 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.2335. Min Act: -0.0000

Data Index: 1493656 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.1616. Min Act: -0.0000

Data Index: 1582974 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.1509. Min Act: -0.0000

Data Index: 1571773 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0696. Min Act: -0.0000

Data Index: 1615238 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.1787. Min Act: -0.0000

Data Index: 1412046 (Python Code)

Max Activating Token Index: 785

Text #12

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0598. Min Act: -0.0000

Data Index: 1625323 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0203. Min Act: -0.0000

Data Index: 1370407 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 2.8270. Min Range: -2.8270

Max Act: 1.9891. Min Act: -0.0000

Data Index: 1429074 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0276. Min Act: -0.0000

Data Index: 1533387 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0111. Min Act: -0.0000

Data Index: 1410808 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0710. Min Act: -0.0000

Data Index: 1488933 (Python Code)

Max Activating Token Index: 406

Text #18

Max Range: 2.8270. Min Range: -2.8270

Max Act: 1.9042. Min Act: -0.0000

Data Index: 1492890 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 2.8270. Min Range: -2.8270

Max Act: 1.9882. Min Act: -0.0000

Data Index: 1496612 (Python Code)

Max Activating Token Index: 912