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

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

Neuron 602 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1055459 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7305. Min Act: -0.0000

Data Index: 4857 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6364. Min Act: -0.0000

Data Index: 780878 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5641. Min Act: -0.0000

Data Index: 477455 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1036078 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1210597 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5365. Min Act: -0.0000

Data Index: 202513 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5156. Min Act: -0.0000

Data Index: 792225 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1063435 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5115. Min Act: -0.0000

Data Index: 312410 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4941. Min Act: -0.0000

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5250. Min Act: -0.0000

Data Index: 912311 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5006. Min Act: -0.0000

Data Index: 663167 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1258641 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4879. Min Act: -0.0000

Data Index: 342013 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4847. Min Act: -0.0000

Data Index: 776938 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4758. Min Act: -0.0000

Data Index: 77772 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4421. Min Act: -0.0000

Data Index: 192632 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4668. Min Act: -0.0000

Data Index: 521804 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1307579 (C4 (Web Text))

Max Activating Token Index: 968