Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1833 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.4899. Min Act: -0.0001

Data Index: 830961 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.4903. Min Act: -0.0002

Data Index: 424293 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.4799. Min Act: -0.0002

Data Index: 1099511 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.4141. Min Act: -0.0002

Data Index: 80712 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.3601. Min Act: -0.0001

Data Index: 825431 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.4384. Min Act: -0.0002

Data Index: 529802 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.3844. Min Act: -0.0002

Data Index: 1097217 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.3742. Min Act: -0.0002

Data Index: 1315993 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.3975. Min Act: -0.0001

Data Index: 75858 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.3513. Min Act: -0.0002

Data Index: 1152758 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2685. Min Act: -0.0001

Data Index: 900993 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.3727. Min Act: -0.0001

Data Index: 753419 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.3705. Min Act: -0.0002

Data Index: 720381 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2667. Min Act: -0.0002

Data Index: 311014 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2702. Min Act: -0.0002

Data Index: 288549 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2314. Min Act: -0.0001

Data Index: 2817 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2928. Min Act: -0.0002

Data Index: 426016 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2198. Min Act: -0.0001

Data Index: 257168 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2465. Min Act: -0.0002

Data Index: 1315876 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2409. Min Act: -0.0002

Data Index: 938771 (C4 (Web Text))

Max Activating Token Index: 9