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

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

Neuron 950 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.9769. Min Act: -0.0000

Data Index: 1585414 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 2.0245. Min Range: -2.0245

Max Act: 2.0245. Min Act: -0.0000

Data Index: 1586574 (Python Code)

Max Activating Token Index: 382

Text #2

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1550453 (Python Code)

Max Activating Token Index: 1019

Text #3

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.6979. Min Act: -0.0000

Data Index: 1529006 (Python Code)

Max Activating Token Index: 90

Text #4

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.6849. Min Act: -0.0000

Data Index: 1558879 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.7826. Min Act: -0.0000

Data Index: 1470846 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.7247. Min Act: -0.0000

Data Index: 1561230 (Python Code)

Max Activating Token Index: 800

Text #7

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.7493. Min Act: -0.0000

Data Index: 1638033 (Python Code)

Max Activating Token Index: 501

Text #8

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.6205. Min Act: -0.0000

Data Index: 428268 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1652249 (Python Code)

Max Activating Token Index: 934

Text #10

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.8811. Min Act: -0.0000

Data Index: 1406305 (Python Code)

Max Activating Token Index: 774

Text #11

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.6338. Min Act: -0.0000

Data Index: 1600619 (Python Code)

Max Activating Token Index: 99

Text #12

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.6117. Min Act: -0.0000

Data Index: 1531024 (Python Code)

Max Activating Token Index: 401

Text #13

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1385577 (Python Code)

Max Activating Token Index: 586

Text #14

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.4427. Min Act: -0.0000

Data Index: 1536253 (Python Code)

Max Activating Token Index: 444

Text #15

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.5230. Min Act: -0.0000

Data Index: 1535198 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.5301. Min Act: -0.0000

Data Index: 1655346 (Python Code)

Max Activating Token Index: 593

Text #17

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1623116 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.4529. Min Act: -0.0000

Data Index: 1441845 (Python Code)

Max Activating Token Index: 515

Text #19

Max Range: 2.0245. Min Range: -2.0245

Max Act: 1.5236. Min Act: -0.0000

Data Index: 765686 (C4 (Web Text))

Max Activating Token Index: 555