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

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

Neuron 3661 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1524399 (Python Code)

Max Activating Token Index: 425

Text #1

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1420856 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0867. Min Act: -0.0000

Data Index: 494812 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1410806 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1377973 (Python Code)

Max Activating Token Index: 905

Text #5

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0830. Min Act: -0.0000

Data Index: 390859 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1074834 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0774. Min Act: -0.0000

Data Index: 110242 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1037783 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0755. Min Act: -0.0000

Data Index: 410962 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0756. Min Act: -0.0000

Data Index: 502355 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1395400 (Python Code)

Max Activating Token Index: 418

Text #12

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1619927 (Python Code)

Max Activating Token Index: 648

Text #13

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0772. Min Act: -0.0000

Data Index: 26226 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1381819 (Python Code)

Max Activating Token Index: 940

Text #15

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1270661 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0788. Min Act: -0.0000

Data Index: 643004 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0689. Min Act: -0.0000

Data Index: 130035 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1186752 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1236352 (C4 (Web Text))

Max Activating Token Index: 1023