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

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

Neuron 60 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0904. Min Act: -0.0002

Data Index: 312396 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0858. Min Act: -0.0002

Data Index: 405537 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0836. Min Act: -0.0002

Data Index: 785667 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0837. Min Act: -0.0002

Data Index: 337935 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0804. Min Act: -0.0002

Data Index: 323500 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0792. Min Act: -0.0002

Data Index: 716886 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0778. Min Act: -0.0002

Data Index: 728649 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0746. Min Act: -0.0002

Data Index: 938596 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0747. Min Act: -0.0002

Data Index: 260757 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0722. Min Act: -0.0002

Data Index: 297472 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1310827 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1239246 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1132426 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0711. Min Act: -0.0002

Data Index: 829438 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0709. Min Act: -0.0003

Data Index: 237630 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0697. Min Act: -0.0002

Data Index: 94075 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0682. Min Act: -0.0002

Data Index: 497799 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1284034 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0683. Min Act: -0.0002

Data Index: 147456 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0683. Min Act: -0.0002

Data Index: 118687 (C4 (Web Text))

Max Activating Token Index: 854