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

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

Neuron 3652 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8607. Min Act: -0.0000

Data Index: 872221 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1086231 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1402437 (Python Code)

Max Activating Token Index: 608

Text #3

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8330. Min Act: -0.0000

Data Index: 766185 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7449. Min Act: -0.0000

Data Index: 851928 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1387920 (Python Code)

Max Activating Token Index: 1022

Text #6

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1360658 (Python Code)

Max Activating Token Index: 394

Text #7

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7724. Min Act: -0.0000

Data Index: 452405 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7219. Min Act: -0.0000

Data Index: 899218 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1474684 (Python Code)

Max Activating Token Index: 758

Text #10

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1180294 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1433705 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7470. Min Act: -0.0000

Data Index: 158448 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1616816 (Python Code)

Max Activating Token Index: 869

Text #14

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1073454 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1229538 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6939. Min Act: -0.0000

Data Index: 865551 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6921. Min Act: -0.0000

Data Index: 566872 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7145. Min Act: -0.0000

Data Index: 885015 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1416346 (Python Code)

Max Activating Token Index: 694