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

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

Neuron 5050 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6804. Min Act: -0.0003

Data Index: 1557577 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6921. Min Act: -0.0002

Data Index: 1416543 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6477. Min Act: -0.0003

Data Index: 1627702 (Python Code)

Max Activating Token Index: 641

Text #3

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6603. Min Act: -0.0003

Data Index: 1523071 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6505. Min Act: -0.0003

Data Index: 1554815 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6572. Min Act: -0.0003

Data Index: 1546097 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6396. Min Act: -0.0003

Data Index: 1573726 (Python Code)

Max Activating Token Index: 257

Text #7

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6282. Min Act: -0.0003

Data Index: 1371503 (Python Code)

Max Activating Token Index: 490

Text #8

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6251. Min Act: -0.0003

Data Index: 1400771 (Python Code)

Max Activating Token Index: 489

Text #9

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6272. Min Act: -0.0003

Data Index: 1613916 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6104. Min Act: -0.0003

Data Index: 1375382 (Python Code)

Max Activating Token Index: 577

Text #11

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6102. Min Act: -0.0003

Data Index: 1554014 (Python Code)

Max Activating Token Index: 428

Text #12

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5991. Min Act: -0.0002

Data Index: 1578727 (Python Code)

Max Activating Token Index: 741

Text #13

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5865. Min Act: -0.0003

Data Index: 1360572 (Python Code)

Max Activating Token Index: 913

Text #14

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5504. Min Act: -0.0003

Data Index: 1555149 (Python Code)

Max Activating Token Index: 163

Text #15

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5317. Min Act: -0.0003

Data Index: 1389099 (Python Code)

Max Activating Token Index: 769

Text #16

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5195. Min Act: -0.0003

Data Index: 1380308 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5014. Min Act: -0.0002

Data Index: 1528310 (Python Code)

Max Activating Token Index: 815

Text #18

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4911. Min Act: -0.0003

Data Index: 1431851 (Python Code)

Max Activating Token Index: 370

Text #19

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4883. Min Act: -0.0002

Data Index: 1377272 (Python Code)

Max Activating Token Index: 795