Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4575 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5558. Min Range: -3.5558

Max Act: 3.1955. Min Act: -0.0000

Data Index: 96392 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 3.5558. Min Range: -3.5558

Max Act: 3.5558. Min Act: -0.0000

Data Index: 778729 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 3.5558. Min Range: -3.5558

Max Act: 3.4346. Min Act: -0.0000

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 3.5558. Min Range: -3.5558

Max Act: 2.6003. Min Act: -0.0000

Data Index: 185187 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 3.5558. Min Range: -3.5558

Max Act: 2.4258. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 3.5558. Min Range: -3.5558

Max Act: 2.2348. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 3.5558. Min Range: -3.5558

Max Act: 2.3458. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 3.5558. Min Range: -3.5558

Max Act: 2.0406. Min Act: -0.0000

Data Index: 259042 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 3.5558. Min Range: -3.5558

Max Act: 2.0341. Min Act: -0.0000

Data Index: 98785 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 3.5558. Min Range: -3.5558

Max Act: 1.8514. Min Act: -0.0000

Data Index: 688853 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 3.5558. Min Range: -3.5558

Max Act: 2.0641. Min Act: -0.0000

Data Index: 1474611 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 3.5558. Min Range: -3.5558

Max Act: 2.0289. Min Act: -0.0000

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 3.5558. Min Range: -3.5558

Max Act: 2.1072. Min Act: -0.0000

Data Index: 180336 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 3.5558. Min Range: -3.5558

Max Act: 1.9444. Min Act: -0.0000

Data Index: 434232 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 3.5558. Min Range: -3.5558

Max Act: 1.9489. Min Act: -0.0000

Data Index: 678615 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 3.5558. Min Range: -3.5558

Max Act: 1.7054. Min Act: 0.0000

Data Index: 1420099 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 3.5558. Min Range: -3.5558

Max Act: 1.8734. Min Act: -0.0000

Data Index: 1044857 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 3.5558. Min Range: -3.5558

Max Act: 1.7617. Min Act: -0.0000

Data Index: 1647907 (Python Code)

Max Activating Token Index: 996

Text #18

Max Range: 3.5558. Min Range: -3.5558

Max Act: 1.7937. Min Act: 0.0000

Data Index: 1479795 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 3.5558. Min Range: -3.5558

Max Act: 1.8072. Min Act: -0.0000

Data Index: 1031796 (C4 (Web Text))

Max Activating Token Index: 947