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

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

Neuron 3657 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1364245 (Python Code)

Max Activating Token Index: 459

Text #1

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1612929 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1433017 (Python Code)

Max Activating Token Index: 628

Text #3

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1578879 (Python Code)

Max Activating Token Index: 232

Text #4

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.5136. Min Act: -0.0000

Data Index: 989845 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1437042 (Python Code)

Max Activating Token Index: 193

Text #6

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1435174 (Python Code)

Max Activating Token Index: 328

Text #7

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4858. Min Act: -0.0000

Data Index: 881609 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1609670 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1347951 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4233. Min Act: -0.0000

Data Index: 299826 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1581361 (Python Code)

Max Activating Token Index: 514

Text #12

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1446599 (Python Code)

Max Activating Token Index: 736

Text #13

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1516877 (Python Code)

Max Activating Token Index: 1012

Text #14

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4204. Min Act: -0.0000

Data Index: 760869 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1562529 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1490143 (Python Code)

Max Activating Token Index: 468

Text #17

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4237. Min Act: -0.0000

Data Index: 242678 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4493. Min Act: -0.0000

Data Index: 174657 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.6907. Min Range: -0.6907

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1369307 (Python Code)

Max Activating Token Index: 80