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

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

Neuron 3660 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: 0.7067. Min Range: -0.7067

Max Act: 0.7067. Min Act: -0.0000

Data Index: 46723 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6906. Min Act: -0.0000

Data Index: 201283 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6230. Min Act: -0.0000

Data Index: 72288 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6265. Min Act: -0.0000

Data Index: 862142 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1192574 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5804. Min Act: -0.0000

Data Index: 290848 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5837. Min Act: -0.0000

Data Index: 441004 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1076197 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5678. Min Act: -0.0000

Data Index: 453755 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5763. Min Act: -0.0000

Data Index: 262013 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5676. Min Act: -0.0000

Data Index: 927217 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5896. Min Act: -0.0000

Data Index: 615711 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5560. Min Act: -0.0000

Data Index: 833058 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5566. Min Act: -0.0000

Data Index: 605473 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1069413 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5296. Min Act: -0.0000

Data Index: 358991 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5540. Min Act: -0.0000

Data Index: 583893 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5417. Min Act: -0.0000

Data Index: 743591 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1310629 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5260. Min Act: -0.0000

Data Index: 390732 (C4 (Web Text))

Max Activating Token Index: 50