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

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

Neuron 5114 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1645822 (Python Code)

Max Activating Token Index: 338

Text #1

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1506918 (Python Code)

Max Activating Token Index: 281

Text #2

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1648492 (Python Code)

Max Activating Token Index: 341

Text #3

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1439559 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1492674 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1524374 (Python Code)

Max Activating Token Index: 508

Text #6

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0819. Min Act: -0.0000

Data Index: 1382758 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1435983 (Python Code)

Max Activating Token Index: 583

Text #8

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1518558 (Python Code)

Max Activating Token Index: 237

Text #9

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1465914 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1571076 (Python Code)

Max Activating Token Index: 321

Text #11

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1531883 (Python Code)

Max Activating Token Index: 131

Text #12

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1601424 (Python Code)

Max Activating Token Index: 516

Text #13

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1386032 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0817. Min Act: -0.0000

Data Index: 1625884 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1436927 (Python Code)

Max Activating Token Index: 679

Text #16

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1493722 (Python Code)

Max Activating Token Index: 734

Text #17

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1504399 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1405194 (Python Code)

Max Activating Token Index: 320

Text #19

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1573847 (Python Code)

Max Activating Token Index: 279