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

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

Neuron 5767 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2692. Min Range: -6.2692

Max Act: 6.2692. Min Act: -0.0000

Data Index: 1362750 (Python Code)

Max Activating Token Index: 343

Text #1

Max Range: 6.2692. Min Range: -6.2692

Max Act: 6.1000. Min Act: -0.0000

Data Index: 1411534 (Python Code)

Max Activating Token Index: 405

Text #2

Max Range: 6.2692. Min Range: -6.2692

Max Act: 6.2389. Min Act: -0.0000

Data Index: 1551315 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 6.2692. Min Range: -6.2692

Max Act: 6.2151. Min Act: -0.0000

Data Index: 1497466 (Python Code)

Max Activating Token Index: 283

Text #4

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.9580. Min Act: -0.0000

Data Index: 1521516 (Python Code)

Max Activating Token Index: 193

Text #5

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.9565. Min Act: -0.0000

Data Index: 1585070 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.3750. Min Act: -0.0000

Data Index: 1420019 (Python Code)

Max Activating Token Index: 526

Text #7

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.5065. Min Act: -0.0000

Data Index: 1596269 (Python Code)

Max Activating Token Index: 354

Text #8

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.0791. Min Act: -0.0000

Data Index: 1608022 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.5969. Min Act: -0.0000

Data Index: 1481213 (Python Code)

Max Activating Token Index: 159

Text #10

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.5621. Min Act: -0.0000

Data Index: 1416521 (Python Code)

Max Activating Token Index: 434

Text #11

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.5419. Min Act: -0.0000

Data Index: 1625439 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.3109. Min Act: -0.0000

Data Index: 1443058 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.4522. Min Act: -0.0000

Data Index: 1616989 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.2820. Min Act: -0.0000

Data Index: 1535250 (Python Code)

Max Activating Token Index: 329

Text #15

Max Range: 6.2692. Min Range: -6.2692

Max Act: 4.9320. Min Act: -0.0000

Data Index: 1503944 (Python Code)

Max Activating Token Index: 719

Text #16

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.0465. Min Act: -0.0000

Data Index: 1442808 (Python Code)

Max Activating Token Index: 582

Text #17

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.0369. Min Act: -0.0000

Data Index: 1442014 (Python Code)

Max Activating Token Index: 699

Text #18

Max Range: 6.2692. Min Range: -6.2692

Max Act: 4.8328. Min Act: -0.0000

Data Index: 1652466 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 6.2692. Min Range: -6.2692

Max Act: 5.3925. Min Act: -0.0000

Data Index: 1617735 (Python Code)

Max Activating Token Index: 317