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

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

Neuron 331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4830. Min Act: -0.0000

Data Index: 81328 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4052. Min Act: -0.0000

Data Index: 997525 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3824. Min Act: -0.0000

Data Index: 778795 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3395. Min Act: -0.0000

Data Index: 955204 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2926. Min Act: -0.0000

Data Index: 57736 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1203075 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2189. Min Act: -0.0001

Data Index: 416881 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2760. Min Act: -0.0000

Data Index: 81 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2663. Min Act: -0.0000

Data Index: 136879 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2734. Min Act: -0.0001

Data Index: 792434 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2767. Min Act: -0.0000

Data Index: 480863 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1111159 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2705. Min Act: -0.0000

Data Index: 75398 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2611. Min Act: -0.0001

Data Index: 830519 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2741. Min Act: -0.0000

Data Index: 809770 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2651. Min Act: -0.0000

Data Index: 196036 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1063093 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2587. Min Act: -0.0000

Data Index: 909040 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1244783 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1158573 (C4 (Web Text))

Max Activating Token Index: 976