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

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

Neuron 1659 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1296718 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0964. Min Act: -0.0000

Data Index: 986339 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0889. Min Act: -0.0000

Data Index: 239402 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1156341 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0907. Min Act: -0.0000

Data Index: 672640 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0770. Min Act: -0.0000

Data Index: 456564 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1152909 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0776. Min Act: -0.0000

Data Index: 968810 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0792. Min Act: -0.0000

Data Index: 137554 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1583501 (Python Code)

Max Activating Token Index: 215

Text #10

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0765. Min Act: -0.0000

Data Index: 360178 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0738. Min Act: -0.0000

Data Index: 660462 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0762. Min Act: -0.0000

Data Index: 814734 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1337969 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1620865 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0736. Min Act: -0.0000

Data Index: 836874 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0673. Min Act: -0.0000

Data Index: 72280 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0696. Min Act: -0.0000

Data Index: 262991 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0663. Min Act: -0.0000

Data Index: 695885 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0679. Min Act: -0.0000

Data Index: 468836 (C4 (Web Text))

Max Activating Token Index: 434