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

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

Neuron 4659 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: 0.7267. Min Range: -0.7267

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1517334 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6525. Min Act: -0.0000

Data Index: 219500 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1542186 (Python Code)

Max Activating Token Index: 657

Text #3

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5867. Min Act: -0.0000

Data Index: 242042 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1367113 (Python Code)

Max Activating Token Index: 488

Text #5

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1030253 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1595298 (Python Code)

Max Activating Token Index: 394

Text #7

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1513307 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1396982 (Python Code)

Max Activating Token Index: 597

Text #9

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6395. Min Act: -0.0000

Data Index: 937221 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1218365 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1492153 (Python Code)

Max Activating Token Index: 587

Text #12

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1561967 (Python Code)

Max Activating Token Index: 310

Text #13

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1455345 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1411781 (Python Code)

Max Activating Token Index: 571

Text #15

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5415. Min Act: -0.0000

Data Index: 747040 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1437088 (Python Code)

Max Activating Token Index: 186

Text #17

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1387811 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1141611 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1376974 (Python Code)

Max Activating Token Index: 831