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

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

Neuron 2692 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0278. Min Range: -4.0278

Max Act: 4.0278. Min Act: -0.0000

Data Index: 1378355 (Python Code)

Max Activating Token Index: 532

Text #1

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.6679. Min Act: -0.0000

Data Index: 1433144 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.3070. Min Act: -0.0000

Data Index: 1647294 (Python Code)

Max Activating Token Index: 357

Text #3

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.4210. Min Act: -0.0000

Data Index: 1405505 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.0067. Min Act: -0.0000

Data Index: 1451411 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.9911. Min Act: -0.0000

Data Index: 1393767 (Python Code)

Max Activating Token Index: 469

Text #6

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.0522. Min Act: -0.0000

Data Index: 1613160 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.9330. Min Act: -0.0000

Data Index: 1646737 (Python Code)

Max Activating Token Index: 389

Text #8

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.0558. Min Act: -0.0000

Data Index: 1475001 (Python Code)

Max Activating Token Index: 280

Text #9

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.8929. Min Act: -0.0000

Data Index: 1459652 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.8727. Min Act: -0.0000

Data Index: 1362147 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.8397. Min Act: -0.0000

Data Index: 1377294 (Python Code)

Max Activating Token Index: 868

Text #12

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.8321. Min Act: -0.0000

Data Index: 1444060 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.8281. Min Act: -0.0000

Data Index: 1532538 (Python Code)

Max Activating Token Index: 609

Text #14

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.6827. Min Act: -0.0000

Data Index: 1633159 (Python Code)

Max Activating Token Index: 868

Text #15

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.7968. Min Act: -0.0000

Data Index: 1480890 (Python Code)

Max Activating Token Index: 985

Text #16

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.6525. Min Act: -0.0000

Data Index: 1563086 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.6232. Min Act: -0.0000

Data Index: 1546343 (Python Code)

Max Activating Token Index: 957

Text #18

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.4723. Min Act: -0.0000

Data Index: 1381437 (Python Code)

Max Activating Token Index: 677

Text #19

Max Range: 4.0278. Min Range: -4.0278

Max Act: 2.6004. Min Act: -0.0000

Data Index: 1486728 (Python Code)

Max Activating Token Index: 1013