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

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

Neuron 2635 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1126694 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.4453. Min Act: -0.0000

Data Index: 257103 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.2686. Min Act: -0.0000

Data Index: 90462 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.1310. Min Act: -0.0000

Data Index: 698321 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0848. Min Act: -0.0000

Data Index: 725365 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.1049. Min Act: -0.0000

Data Index: 120887 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0502. Min Act: -0.0000

Data Index: 823721 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1047890 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9695. Min Act: -0.0000

Data Index: 664960 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9884. Min Act: -0.0000

Data Index: 560555 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9952. Min Act: -0.0000

Data Index: 857920 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1061708 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9953. Min Act: -0.0000

Data Index: 761158 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1293953 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9975. Min Act: -0.0000

Data Index: 17632 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9912. Min Act: -0.0000

Data Index: 291038 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1041718 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9510. Min Act: -0.0001

Data Index: 496853 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0315. Min Act: -0.0000

Data Index: 708135 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1353677 (C4 (Web Text))

Max Activating Token Index: 835