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

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

Neuron 19 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: 1.7888. Min Range: -1.7888

Max Act: 1.7888. Min Act: -0.0000

Data Index: 920216 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4962. Min Act: -0.0000

Data Index: 852944 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4465. Min Act: -0.0000

Data Index: 1043569 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1321772 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.2945. Min Act: -0.0000

Data Index: 211787 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.2567. Min Act: -0.0000

Data Index: 306482 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.2752. Min Act: -0.0000

Data Index: 768418 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.3111. Min Act: -0.0000

Data Index: 286237 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.1136. Min Act: -0.0000

Data Index: 852415 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.1875. Min Act: -0.0000

Data Index: 862049 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1236445 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.1034. Min Act: -0.0000

Data Index: 976016 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0404. Min Act: -0.0000

Data Index: 861669 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0399. Min Act: -0.0000

Data Index: 671100 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0706. Min Act: -0.0000

Data Index: 952441 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0229. Min Act: -0.0000

Data Index: 992342 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0734. Min Act: -0.0000

Data Index: 460664 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1212445 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0397. Min Act: -0.0000

Data Index: 166956 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1051276 (C4 (Web Text))

Max Activating Token Index: 756