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

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

Neuron 4856 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: 2.2937. Min Range: -2.2937

Max Act: 2.2937. Min Act: -0.0000

Data Index: 1431730 (Python Code)

Max Activating Token Index: 823

Text #1

Max Range: 2.2937. Min Range: -2.2937

Max Act: 2.0551. Min Act: -0.0000

Data Index: 1481999 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1584646 (Python Code)

Max Activating Token Index: 604

Text #3

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.7165. Min Act: -0.0000

Data Index: 1607931 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1387150 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.5328. Min Act: -0.0000

Data Index: 1441155 (Python Code)

Max Activating Token Index: 383

Text #6

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1613971 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.5307. Min Act: -0.0000

Data Index: 1556167 (Python Code)

Max Activating Token Index: 500

Text #8

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.6310. Min Act: -0.0000

Data Index: 1564965 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.5272. Min Act: -0.0000

Data Index: 1455541 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.5753. Min Act: -0.0000

Data Index: 1650630 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.4816. Min Act: -0.0000

Data Index: 1548713 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.5684. Min Act: -0.0000

Data Index: 1621273 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.4626. Min Act: -0.0000

Data Index: 1407018 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.4321. Min Act: -0.0000

Data Index: 1557870 (Python Code)

Max Activating Token Index: 497

Text #15

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.3420. Min Act: -0.0000

Data Index: 1626129 (Python Code)

Max Activating Token Index: 446

Text #16

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.4249. Min Act: -0.0000

Data Index: 1469903 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.4558. Min Act: -0.0000

Data Index: 1614238 (Python Code)

Max Activating Token Index: 438

Text #18

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1606163 (Python Code)

Max Activating Token Index: 600

Text #19

Max Range: 2.2937. Min Range: -2.2937

Max Act: 1.3732. Min Act: -0.0000

Data Index: 1381462 (Python Code)

Max Activating Token Index: 340