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

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

Neuron 4094 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.5428. Min Act: -0.0001

Data Index: 938416 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.5642. Min Act: -0.0001

Data Index: 493729 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.5430. Min Act: -0.0001

Data Index: 889308 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2867. Min Act: -0.0001

Data Index: 620717 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2959. Min Act: -0.0001

Data Index: 1097009 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2251. Min Act: -0.0001

Data Index: 1258620 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2289. Min Act: -0.0001

Data Index: 1648531 (Python Code)

Max Activating Token Index: 350

Text #7

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2504. Min Act: -0.0001

Data Index: 613842 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.1439. Min Act: -0.0001

Data Index: 812280 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.1468. Min Act: -0.0001

Data Index: 1565926 (Python Code)

Max Activating Token Index: 212

Text #10

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.1451. Min Act: -0.0001

Data Index: 1541162 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.1506. Min Act: -0.0001

Data Index: 1498607 (Python Code)

Max Activating Token Index: 88

Text #12

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.1155. Min Act: -0.0001

Data Index: 589853 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.1991. Min Act: -0.0001

Data Index: 1483453 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.1031. Min Act: -0.0001

Data Index: 645394 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.1379. Min Act: -0.0001

Data Index: 795363 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.0760. Min Act: -0.0001

Data Index: 343354 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.0552. Min Act: -0.0001

Data Index: 1477851 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.0516. Min Act: -0.0001

Data Index: 49470 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.0812. Min Act: -0.0001

Data Index: 1060628 (C4 (Web Text))

Max Activating Token Index: 747