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

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

Neuron 3338 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0327. Min Range: -1.0327

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1197964 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9583. Min Act: -0.0000

Data Index: 866367 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8953. Min Act: -0.0000

Data Index: 829791 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9472. Min Act: -0.0000

Data Index: 397988 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8691. Min Act: -0.0000

Data Index: 955061 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9012. Min Act: -0.0000

Data Index: 547294 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1099037 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9596. Min Act: -0.0000

Data Index: 810215 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1275271 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8245. Min Act: -0.0000

Data Index: 850382 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7367. Min Act: -0.0000

Data Index: 275113 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1039666 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7779. Min Act: -0.0000

Data Index: 832205 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.6347. Min Act: -0.0000

Data Index: 137708 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1285390 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7611. Min Act: -0.0000

Data Index: 182990 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1539409 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1297590 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7382. Min Act: -0.0000

Data Index: 709734 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8278. Min Act: -0.0000

Data Index: 739667 (C4 (Web Text))

Max Activating Token Index: 101