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

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

Neuron 1491 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.6831. Min Act: -0.0001

Data Index: 1331748 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.5863. Min Act: -0.0001

Data Index: 478602 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.6293. Min Act: -0.0001

Data Index: 1449739 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.6293. Min Act: -0.0000

Data Index: 1415022 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.5454. Min Act: -0.0001

Data Index: 1642407 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.5454. Min Act: -0.0000

Data Index: 1517123 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.2445. Min Act: -0.0000

Data Index: 1636851 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.5729. Min Act: -0.0001

Data Index: 1479895 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.1731. Min Act: -0.0001

Data Index: 1589066 (Python Code)

Max Activating Token Index: 221

Text #9

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4777. Min Act: -0.0001

Data Index: 1500250 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4777. Min Act: -0.0000

Data Index: 1498582 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.3904. Min Act: -0.0000

Data Index: 1507054 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.5666. Min Act: -0.0000

Data Index: 548076 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4870. Min Act: -0.0000

Data Index: 296864 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4865. Min Act: -0.0001

Data Index: 1327265 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.5269. Min Act: -0.0001

Data Index: 370177 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4746. Min Act: -0.0001

Data Index: 1410798 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4753. Min Act: -0.0000

Data Index: 1641298 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4753. Min Act: -0.0001

Data Index: 1441059 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1372700 (Python Code)

Max Activating Token Index: 9