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

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

Neuron 4039 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: 3.6252. Min Range: -3.6252

Max Act: 3.5804. Min Act: -0.0000

Data Index: 68945 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.6252. Min Act: -0.0000

Data Index: 270230 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.3167. Min Act: -0.0000

Data Index: 800988 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.4064. Min Act: -0.0000

Data Index: 34973 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.0268. Min Act: -0.0000

Data Index: 1585001 (Python Code)

Max Activating Token Index: 664

Text #5

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.8505. Min Act: -0.0000

Data Index: 1102861 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.0634. Min Act: -0.0000

Data Index: 862839 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.0133. Min Act: -0.0000

Data Index: 1208690 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.7600. Min Act: -0.0000

Data Index: 444030 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.7431. Min Act: -0.0000

Data Index: 1403163 (Python Code)

Max Activating Token Index: 857

Text #10

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.8789. Min Act: -0.0000

Data Index: 345247 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.7322. Min Act: -0.0000

Data Index: 308779 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.5197. Min Act: -0.0000

Data Index: 1198384 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.5637. Min Act: -0.0000

Data Index: 680424 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.5640. Min Act: -0.0000

Data Index: 223848 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.5585. Min Act: -0.0000

Data Index: 1253146 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.5619. Min Act: -0.0000

Data Index: 312875 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.5526. Min Act: -0.0000

Data Index: 1103164 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.5620. Min Act: -0.0000

Data Index: 1131522 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 3.6252. Min Range: -3.6252

Max Act: 2.5234. Min Act: -0.0000

Data Index: 935416 (C4 (Web Text))

Max Activating Token Index: 596