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

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

Neuron 2375 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.1338. Min Act: -0.0001

Data Index: 196465 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.1372. Min Act: -0.0001

Data Index: 1376897 (Python Code)

Max Activating Token Index: 871

Text #2

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0908. Min Act: -0.0001

Data Index: 1399583 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0231. Min Act: -0.0001

Data Index: 1425128 (Python Code)

Max Activating Token Index: 135

Text #4

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0826. Min Act: -0.0001

Data Index: 863103 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9500. Min Act: -0.0001

Data Index: 1413446 (Python Code)

Max Activating Token Index: 786

Text #6

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9222. Min Act: -0.0001

Data Index: 1614140 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0134. Min Act: -0.0001

Data Index: 1580424 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9557. Min Act: -0.0001

Data Index: 1380316 (Python Code)

Max Activating Token Index: 956

Text #9

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0244. Min Act: -0.0001

Data Index: 1476697 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9269. Min Act: -0.0001

Data Index: 637879 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8071. Min Act: -0.0001

Data Index: 1637371 (Python Code)

Max Activating Token Index: 139

Text #12

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8563. Min Act: -0.0001

Data Index: 1529480 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8008. Min Act: -0.0001

Data Index: 1467430 (Python Code)

Max Activating Token Index: 221

Text #14

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.7781. Min Act: -0.0001

Data Index: 1404460 (Python Code)

Max Activating Token Index: 313

Text #15

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8799. Min Act: -0.0001

Data Index: 1044932 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9067. Min Act: -0.0001

Data Index: 1363443 (Python Code)

Max Activating Token Index: 921

Text #17

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.7989. Min Act: -0.0001

Data Index: 1592195 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8111. Min Act: -0.0001

Data Index: 1195435 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8455. Min Act: -0.0001

Data Index: 1481577 (Python Code)

Max Activating Token Index: 190