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

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

Neuron 829 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0405. Min Range: -1.0405

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1593506 (Python Code)

Max Activating Token Index: 327

Text #1

Max Range: 1.0405. Min Range: -1.0405

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1434770 (Python Code)

Max Activating Token Index: 629

Text #2

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1349928 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1397803 (Python Code)

Max Activating Token Index: 209

Text #4

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1472995 (Python Code)

Max Activating Token Index: 313

Text #5

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8393. Min Act: -0.0000

Data Index: 792249 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8870. Min Act: -0.0000

Data Index: 844104 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1404279 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8602. Min Act: -0.0000

Data Index: 690802 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8862. Min Act: -0.0000

Data Index: 547659 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.9099. Min Act: -0.0000

Data Index: 161526 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8834. Min Act: -0.0000

Data Index: 962931 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.9012. Min Act: 0.0000

Data Index: 1541071 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1287090 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1049508 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8352. Min Act: 0.0001

Data Index: 1482417 (Python Code)

Max Activating Token Index: 523

Text #16

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1277113 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8275. Min Act: 0.0000

Data Index: 1545804 (Python Code)

Max Activating Token Index: 550

Text #18

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1516005 (Python Code)

Max Activating Token Index: 682

Text #19

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8420. Min Act: 0.0000

Data Index: 1414749 (Python Code)

Max Activating Token Index: 727