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

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

Neuron 1471 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3340. Min Act: -0.0000

Data Index: 871764 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3160. Min Act: -0.0000

Data Index: 718310 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1306752 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1234741 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2803. Min Act: -0.0000

Data Index: 466050 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1235873 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2840. Min Act: -0.0000

Data Index: 584855 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2693. Min Act: -0.0000

Data Index: 68943 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1270148 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2629. Min Act: -0.0000

Data Index: 596076 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2890. Min Act: -0.0000

Data Index: 532680 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2703. Min Act: -0.0000

Data Index: 513633 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1153153 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2637. Min Act: -0.0000

Data Index: 674992 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2547. Min Act: -0.0000

Data Index: 930934 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2543. Min Act: -0.0000

Data Index: 896564 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2611. Min Act: -0.0000

Data Index: 665450 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2535. Min Act: -0.0000

Data Index: 776004 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1183084 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2591. Min Act: -0.0000

Data Index: 561012 (C4 (Web Text))

Max Activating Token Index: 484