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

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

Neuron 2231 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1210. Min Range: -2.1210

Max Act: 2.1210. Min Act: -0.0000

Data Index: 1557817 (Python Code)

Max Activating Token Index: 397

Text #1

Max Range: 2.1210. Min Range: -2.1210

Max Act: 2.0674. Min Act: -0.0000

Data Index: 1597948 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.7745. Min Act: -0.0000

Data Index: 1375664 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.6254. Min Act: -0.0000

Data Index: 1495561 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.6086. Min Act: -0.0000

Data Index: 1520030 (Python Code)

Max Activating Token Index: 307

Text #5

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1514928 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.4321. Min Act: -0.0000

Data Index: 1366644 (Python Code)

Max Activating Token Index: 379

Text #7

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3785. Min Act: -0.0000

Data Index: 1532795 (Python Code)

Max Activating Token Index: 831

Text #8

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1461789 (Python Code)

Max Activating Token Index: 657

Text #9

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3648. Min Act: -0.0000

Data Index: 1405689 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3157. Min Act: -0.0000

Data Index: 1553937 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.4650. Min Act: -0.0000

Data Index: 1613083 (Python Code)

Max Activating Token Index: 880

Text #12

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1577993 (Python Code)

Max Activating Token Index: 392

Text #13

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1427168 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3455. Min Act: -0.0000

Data Index: 1393797 (Python Code)

Max Activating Token Index: 200

Text #15

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3424. Min Act: -0.0000

Data Index: 1405953 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1406223 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1633930 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1383956 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 2.1210. Min Range: -2.1210

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1457270 (Python Code)

Max Activating Token Index: 140