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

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

Neuron 3911 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2825. Min Act: -0.0003

Data Index: 1081745 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2671. Min Act: -0.0003

Data Index: 287738 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2799. Min Act: -0.0003

Data Index: 779601 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2764. Min Act: -0.0003

Data Index: 1067380 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2760. Min Act: -0.0003

Data Index: 1245641 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2644. Min Act: -0.0003

Data Index: 532289 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2825. Min Act: -0.0003

Data Index: 390571 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2692. Min Act: -0.0003

Data Index: 1147956 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2790. Min Act: -0.0003

Data Index: 830646 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2692. Min Act: -0.0003

Data Index: 194950 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2877. Min Act: -0.0003

Data Index: 32668 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2778. Min Act: -0.0003

Data Index: 458497 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2606. Min Act: -0.0003

Data Index: 451617 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2615. Min Act: -0.0003

Data Index: 238024 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2648. Min Act: -0.0003

Data Index: 510816 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2705. Min Act: -0.0003

Data Index: 395 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2682. Min Act: -0.0003

Data Index: 564922 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2586. Min Act: -0.0003

Data Index: 109584 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2585. Min Act: -0.0003

Data Index: 923097 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2650. Min Act: -0.0003

Data Index: 124585 (C4 (Web Text))

Max Activating Token Index: 536