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

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

Neuron 4722 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.9995. Min Act: 0.0000

Data Index: 1542233 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.9272. Min Act: -0.0000

Data Index: 531733 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1471730 (Python Code)

Max Activating Token Index: 372

Text #3

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.8751. Min Act: -0.0000

Data Index: 21961 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1062406 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1422231 (Python Code)

Max Activating Token Index: 993

Text #6

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.8606. Min Act: -0.0000

Data Index: 729455 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1609835 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1474783 (Python Code)

Max Activating Token Index: 170

Text #9

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1545805 (Python Code)

Max Activating Token Index: 662

Text #10

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1524794 (Python Code)

Max Activating Token Index: 492

Text #11

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1575170 (Python Code)

Max Activating Token Index: 880

Text #12

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1534712 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6989. Min Act: -0.0000

Data Index: 425939 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1484939 (Python Code)

Max Activating Token Index: 337

Text #15

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7258. Min Act: -0.0000

Data Index: 903141 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1619755 (Python Code)

Max Activating Token Index: 333

Text #17

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1425544 (Python Code)

Max Activating Token Index: 823

Text #18

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1481143 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1444633 (Python Code)

Max Activating Token Index: 210