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

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

Neuron 648 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.5498. Min Act: -0.0000

Data Index: 1583439 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1534168 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1455340 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1463873 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1528535 (Python Code)

Max Activating Token Index: 429

Text #5

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1440861 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1469783 (Python Code)

Max Activating Token Index: 546

Text #7

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1655962 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1639265 (Python Code)

Max Activating Token Index: 484

Text #9

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1645408 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 1.5498. Min Range: -1.5498

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1446618 (Python Code)

Max Activating Token Index: 989

Text #11

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.0265. Min Act: -0.0000

Data Index: 1603162 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 1.5498. Min Range: -1.5498

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1391996 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 1.5498. Min Range: -1.5498

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1498981 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 1.5498. Min Range: -1.5498

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1435995 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1470238 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 1.5498. Min Range: -1.5498

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1394746 (Python Code)

Max Activating Token Index: 803

Text #17

Max Range: 1.5498. Min Range: -1.5498

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1653593 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 1.5498. Min Range: -1.5498

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1588069 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 1.5498. Min Range: -1.5498

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1463319 (Python Code)

Max Activating Token Index: 405