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

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

Neuron 679 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0294. Min Range: -2.0294

Max Act: 2.0294. Min Act: -0.0000

Data Index: 23418 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 2.0294. Min Range: -2.0294

Max Act: 2.0099. Min Act: -0.0000

Data Index: 1339170 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.7718. Min Act: -0.0000

Data Index: 316338 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.7963. Min Act: -0.0000

Data Index: 1142539 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.7777. Min Act: -0.0000

Data Index: 211265 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.7879. Min Act: -0.0000

Data Index: 764571 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.7369. Min Act: -0.0000

Data Index: 1048379 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.6853. Min Act: -0.0000

Data Index: 273518 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.6641. Min Act: -0.0000

Data Index: 697019 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.6531. Min Act: -0.0000

Data Index: 1019330 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.5500. Min Act: -0.0000

Data Index: 825818 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.5959. Min Act: -0.0000

Data Index: 79260 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.5939. Min Act: -0.0000

Data Index: 406297 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.5365. Min Act: -0.0000

Data Index: 473717 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.5808. Min Act: -0.0000

Data Index: 1036049 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.5585. Min Act: -0.0000

Data Index: 309116 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.5120. Min Act: -0.0000

Data Index: 191491 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.5384. Min Act: -0.0000

Data Index: 307920 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.4744. Min Act: -0.0000

Data Index: 1250381 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 2.0294. Min Range: -2.0294

Max Act: 1.4706. Min Act: -0.0000

Data Index: 58034 (C4 (Web Text))

Max Activating Token Index: 486