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

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

Neuron 2785 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.3578. Min Act: -0.0000

Data Index: 571254 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.3378. Min Act: -0.0000

Data Index: 532539 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1099938 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2948. Min Act: -0.0000

Data Index: 238368 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2957. Min Act: -0.0000

Data Index: 331539 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2827. Min Act: -0.0000

Data Index: 576817 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.3016. Min Act: -0.0000

Data Index: 584302 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2766. Min Act: -0.0000

Data Index: 330472 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2772. Min Act: -0.0000

Data Index: 251107 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2845. Min Act: -0.0000

Data Index: 608351 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2711. Min Act: -0.0000

Data Index: 100501 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1268698 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1158427 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2721. Min Act: -0.0000

Data Index: 745917 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1145358 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2718. Min Act: -0.0000

Data Index: 874156 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1230450 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2673. Min Act: -0.0000

Data Index: 132838 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2674. Min Act: -0.0000

Data Index: 998533 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1193133 (C4 (Web Text))

Max Activating Token Index: 223