Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3503 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1521447 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1448642 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1428943 (Python Code)

Max Activating Token Index: 477

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1431163 (Python Code)

Max Activating Token Index: 150

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1491605 (Python Code)

Max Activating Token Index: 935

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1559834 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1555539 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1632533 (Python Code)

Max Activating Token Index: 934

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1370507 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1616702 (Python Code)

Max Activating Token Index: 230

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1447021 (Python Code)

Max Activating Token Index: 472

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1397353 (Python Code)

Max Activating Token Index: 893

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1652651 (Python Code)

Max Activating Token Index: 666

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1610936 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1481070 (Python Code)

Max Activating Token Index: 374

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1581567 (Python Code)

Max Activating Token Index: 406

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1609438 (Python Code)

Max Activating Token Index: 667

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1584217 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1509026 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1450690 (Python Code)

Max Activating Token Index: 914