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

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

Neuron 3646 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1444968 (Python Code)

Max Activating Token Index: 381

Text #1

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1370024 (Python Code)

Max Activating Token Index: 956

Text #2

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1511117 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1593120 (Python Code)

Max Activating Token Index: 907

Text #4

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0782. Min Act: -0.0000

Data Index: 974420 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1494065 (Python Code)

Max Activating Token Index: 258

Text #6

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0770. Min Act: -0.0000

Data Index: 961044 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1411893 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1541010 (Python Code)

Max Activating Token Index: 840

Text #9

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1424146 (Python Code)

Max Activating Token Index: 138

Text #10

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1449848 (Python Code)

Max Activating Token Index: 460

Text #11

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0630. Min Act: -0.0000

Data Index: 1135097 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0609. Min Act: -0.0000

Data Index: 880683 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1635929 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1371887 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1317023 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1353991 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0602. Min Act: -0.0000

Data Index: 429884 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1511161 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1558557 (Python Code)

Max Activating Token Index: 271