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

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

Neuron 1598 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.5205. Min Act: -0.0000

Data Index: 1396434 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1592666 (Python Code)

Max Activating Token Index: 804

Text #2

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.3518. Min Act: 0.0001

Data Index: 1653433 (Python Code)

Max Activating Token Index: 486

Text #3

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2801. Min Act: -0.0001

Data Index: 1378357 (Python Code)

Max Activating Token Index: 264

Text #4

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1499809 (Python Code)

Max Activating Token Index: 260

Text #5

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1416939 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1837. Min Act: -0.0000

Data Index: 1645663 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1389430 (Python Code)

Max Activating Token Index: 830

Text #8

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1537543 (Python Code)

Max Activating Token Index: 873

Text #9

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1480647 (Python Code)

Max Activating Token Index: 662

Text #10

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1588232 (Python Code)

Max Activating Token Index: 738

Text #11

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1444126 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1422. Min Act: 0.0000

Data Index: 1406744 (Python Code)

Max Activating Token Index: 408

Text #13

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1437. Min Act: -0.0001

Data Index: 1423845 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.0141. Min Act: -0.0001

Data Index: 1430022 (Python Code)

Max Activating Token Index: 804

Text #15

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1645909 (Python Code)

Max Activating Token Index: 388

Text #16

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1555349 (Python Code)

Max Activating Token Index: 133

Text #17

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.0206. Min Act: -0.0001

Data Index: 1430526 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1525510 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1502443 (Python Code)

Max Activating Token Index: 311