Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1512 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: 0.0000

Data Index: 273609 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0836. Min Act: -0.0000

Data Index: 531107 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0778. Min Act: -0.0000

Data Index: 733915 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0797. Min Act: 0.0000

Data Index: 255857 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0782. Min Act: -0.0000

Data Index: 57939 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0790. Min Act: -0.0000

Data Index: 129089 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0771. Min Act: 0.0000

Data Index: 791096 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0711. Min Act: 0.0000

Data Index: 823684 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0737. Min Act: 0.0001

Data Index: 1022276 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0719. Min Act: 0.0000

Data Index: 628898 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0711. Min Act: 0.0000

Data Index: 732432 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0694. Min Act: -0.0000

Data Index: 255382 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0675. Min Act: -0.0000

Data Index: 700228 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0713. Min Act: 0.0000

Data Index: 772453 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0677. Min Act: 0.0000

Data Index: 152529 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0651. Min Act: -0.0000

Data Index: 116768 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0671. Min Act: 0.0001

Data Index: 1215165 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0639. Min Act: 0.0000

Data Index: 1154217 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0630. Min Act: -0.0000

Data Index: 99606 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1079799 (C4 (Web Text))

Max Activating Token Index: 903