Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 557 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0002

Data Index: 254091 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0768. Min Act: -0.0002

Data Index: 395451 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1281564 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0748. Min Act: -0.0002

Data Index: 490137 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0736. Min Act: -0.0002

Data Index: 232633 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0725. Min Act: -0.0002

Data Index: 630261 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0747. Min Act: -0.0002

Data Index: 237136 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0719. Min Act: -0.0002

Data Index: 574630 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0708. Min Act: -0.0002

Data Index: 691712 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0707. Min Act: -0.0002

Data Index: 318214 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0713. Min Act: -0.0001

Data Index: 200207 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1589597 (Python Code)

Max Activating Token Index: 206

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0725. Min Act: -0.0002

Data Index: 156960 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0700. Min Act: -0.0002

Data Index: 498285 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0726. Min Act: -0.0002

Data Index: 556636 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1161621 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0722. Min Act: -0.0002

Data Index: 564079 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0676. Min Act: -0.0002

Data Index: 274715 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0694. Min Act: -0.0002

Data Index: 797674 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0670. Min Act: -0.0002

Data Index: 534789 (C4 (Web Text))

Max Activating Token Index: 356