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

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

Neuron 4330 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1918. Min Range: -1.1918

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1600334 (Python Code)

Max Activating Token Index: 826

Text #1

Max Range: 1.1918. Min Range: -1.1918

Max Act: 1.0958. Min Act: -0.0000

Data Index: 797011 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.1918. Min Range: -1.1918

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1424836 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 1.1918. Min Range: -1.1918

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1616440 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 1.1918. Min Range: -1.1918

Max Act: 1.0022. Min Act: -0.0000

Data Index: 1363650 (Python Code)

Max Activating Token Index: 968

Text #5

Max Range: 1.1918. Min Range: -1.1918

Max Act: 1.0602. Min Act: -0.0000

Data Index: 821665 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1442441 (Python Code)

Max Activating Token Index: 494

Text #7

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1408656 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1532323 (Python Code)

Max Activating Token Index: 891

Text #9

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1380766 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1425061 (Python Code)

Max Activating Token Index: 523

Text #11

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1471875 (Python Code)

Max Activating Token Index: 601

Text #12

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1367019 (Python Code)

Max Activating Token Index: 240

Text #13

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1565899 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1458364 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1401903 (Python Code)

Max Activating Token Index: 576

Text #16

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1637615 (Python Code)

Max Activating Token Index: 558

Text #17

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1586945 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1587488 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 1.1918. Min Range: -1.1918

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1397421 (Python Code)

Max Activating Token Index: 602