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

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

Neuron 615 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.8449. Min Range: -9.8449

Max Act: 9.8449. Min Act: -0.0000

Data Index: 763187 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 9.8449. Min Range: -9.8449

Max Act: 9.8365. Min Act: -0.0000

Data Index: 391457 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 9.8449. Min Range: -9.8449

Max Act: 9.8362. Min Act: -0.0000

Data Index: 208214 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 9.8449. Min Range: -9.8449

Max Act: 9.8142. Min Act: -0.0000

Data Index: 949234 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 9.8449. Min Range: -9.8449

Max Act: 9.5580. Min Act: -0.0000

Data Index: 1163846 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 9.8449. Min Range: -9.8449

Max Act: 9.1706. Min Act: -0.0001

Data Index: 153941 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 9.8449. Min Range: -9.8449

Max Act: 9.4254. Min Act: -0.0001

Data Index: 14515 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 9.8449. Min Range: -9.8449

Max Act: 9.1133. Min Act: -0.0000

Data Index: 639507 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.8579. Min Act: -0.0000

Data Index: 704345 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.8366. Min Act: -0.0000

Data Index: 31524 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.6423. Min Act: -0.0000

Data Index: 86773 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.8073. Min Act: -0.0001

Data Index: 895044 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.5580. Min Act: -0.0000

Data Index: 1240049 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.5838. Min Act: -0.0001

Data Index: 601205 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.6967. Min Act: -0.0001

Data Index: 1035717 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.3697. Min Act: -0.0001

Data Index: 1302871 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.1328. Min Act: -0.0000

Data Index: 612485 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 9.8449. Min Range: -9.8449

Max Act: 8.0378. Min Act: -0.0000

Data Index: 1342800 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 9.8449. Min Range: -9.8449

Max Act: 7.8317. Min Act: -0.0000

Data Index: 580982 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 9.8449. Min Range: -9.8449

Max Act: 7.7333. Min Act: -0.0000

Data Index: 1168865 (C4 (Web Text))

Max Activating Token Index: 199