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

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

Neuron 5616 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: 1.3391. Min Range: -1.3391

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1097672 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.3391. Min Range: -1.3391

Max Act: 1.3069. Min Act: -0.0000

Data Index: 304417 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 1.3391. Min Range: -1.3391

Max Act: 1.1711. Min Act: -0.0000

Data Index: 299320 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 1.3391. Min Range: -1.3391

Max Act: 1.1193. Min Act: -0.0001

Data Index: 1527594 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 1.3391. Min Range: -1.3391

Max Act: 1.1643. Min Act: -0.0000

Data Index: 482998 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 1.3391. Min Range: -1.3391

Max Act: 1.0202. Min Act: -0.0000

Data Index: 821343 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 1.3391. Min Range: -1.3391

Max Act: 1.1840. Min Act: -0.0000

Data Index: 1248212 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 1.3391. Min Range: -1.3391

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1358591 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.3391. Min Range: -1.3391

Max Act: 1.0444. Min Act: -0.0000

Data Index: 819944 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1093104 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 1.3391. Min Range: -1.3391

Max Act: 1.0049. Min Act: -0.0000

Data Index: 808997 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.9719. Min Act: -0.0000

Data Index: 118795 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.9341. Min Act: -0.0001

Data Index: 993678 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1042612 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.9770. Min Act: -0.0000

Data Index: 916512 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1035519 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.8917. Min Act: -0.0000

Data Index: 535619 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.9442. Min Act: -0.0001

Data Index: 635139 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.9274. Min Act: -0.0000

Data Index: 507601 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 1.3391. Min Range: -1.3391

Max Act: 0.8810. Min Act: -0.0001

Data Index: 214173 (C4 (Web Text))

Max Activating Token Index: 674