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

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

Neuron 2446 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1537. Min Act: -0.0002

Data Index: 1370282 (Python Code)

Max Activating Token Index: 508

Text #1

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1415352 (Python Code)

Max Activating Token Index: 796

Text #2

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1410639 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1394848 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1450227 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1391033 (Python Code)

Max Activating Token Index: 396

Text #6

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1402136 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1452465 (Python Code)

Max Activating Token Index: 196

Text #8

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1488546 (Python Code)

Max Activating Token Index: 834

Text #9

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1570105 (Python Code)

Max Activating Token Index: 371

Text #10

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1533707 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0878. Min Act: -0.0001

Data Index: 1647212 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1520291 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1415384 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1529902 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1646848 (Python Code)

Max Activating Token Index: 324

Text #16

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1383944 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1451078 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1362669 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1524387 (Python Code)

Max Activating Token Index: 780