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

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

Neuron 3390 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0779. Min Act: -0.0002

Data Index: 755876 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0782. Min Act: -0.0002

Data Index: 416291 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1053785 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0707. Min Act: -0.0002

Data Index: 840227 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1139876 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0657. Min Act: -0.0002

Data Index: 128908 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1090877 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0595. Min Act: -0.0002

Data Index: 196264 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0601. Min Act: -0.0002

Data Index: 667373 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0562. Min Act: -0.0002

Data Index: 742982 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0596. Min Act: -0.0002

Data Index: 206928 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1324225 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1125808 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1005892 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0542. Min Act: -0.0002

Data Index: 28155 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0524. Min Act: -0.0002

Data Index: 366884 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0555. Min Act: -0.0002

Data Index: 894563 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1022179 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0510. Min Act: -0.0002

Data Index: 435824 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0514. Min Act: -0.0002

Data Index: 297071 (C4 (Web Text))

Max Activating Token Index: 425