Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1197 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2347. Min Act: 0.0000

Data Index: 1521777 (Python Code)

Max Activating Token Index: 833

Text #1

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2378. Min Act: -0.0001

Data Index: 1465826 (Python Code)

Max Activating Token Index: 372

Text #2

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1550882 (Python Code)

Max Activating Token Index: 290

Text #3

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1383448 (Python Code)

Max Activating Token Index: 869

Text #4

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1376545 (Python Code)

Max Activating Token Index: 794

Text #5

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1894. Min Act: 0.0002

Data Index: 1555945 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1869. Min Act: -0.0001

Data Index: 880282 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1849. Min Act: 0.0001

Data Index: 1546740 (Python Code)

Max Activating Token Index: 122

Text #8

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1444971 (Python Code)

Max Activating Token Index: 510

Text #9

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1748. Min Act: -0.0001

Data Index: 448191 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1800. Min Act: -0.0001

Data Index: 1123510 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1768. Min Act: 0.0000

Data Index: 1490592 (Python Code)

Max Activating Token Index: 193

Text #12

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1368918 (Python Code)

Max Activating Token Index: 1014

Text #13

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1745. Min Act: 0.0000

Data Index: 1588933 (Python Code)

Max Activating Token Index: 414

Text #14

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1708. Min Act: -0.0001

Data Index: 1378053 (Python Code)

Max Activating Token Index: 505

Text #15

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1734. Min Act: 0.0001

Data Index: 1469196 (Python Code)

Max Activating Token Index: 131

Text #16

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1620. Min Act: -0.0001

Data Index: 70146 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1624. Min Act: 0.0001

Data Index: 1623247 (Python Code)

Max Activating Token Index: 788

Text #18

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1629. Min Act: -0.0001

Data Index: 173594 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1640808 (Python Code)

Max Activating Token Index: 880