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

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

Neuron 5697 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: 1.6837. Min Range: -1.6837

Max Act: 1.6837. Min Act: -0.0000

Data Index: 1485999 (Python Code)

Max Activating Token Index: 118

Text #1

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1440934 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.3902. Min Act: -0.0000

Data Index: 1616486 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1477627 (Python Code)

Max Activating Token Index: 736

Text #4

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.3302. Min Act: -0.0000

Data Index: 1536856 (Python Code)

Max Activating Token Index: 674

Text #5

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.2435. Min Act: -0.0000

Data Index: 1606110 (Python Code)

Max Activating Token Index: 669

Text #6

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1529903 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.0796. Min Act: -0.0000

Data Index: 1459926 (Python Code)

Max Activating Token Index: 124

Text #8

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1362525 (Python Code)

Max Activating Token Index: 624

Text #9

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1451714 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.0848. Min Act: -0.0000

Data Index: 1446053 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1410438 (Python Code)

Max Activating Token Index: 795

Text #12

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.1014. Min Act: -0.0000

Data Index: 1586377 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1459518 (Python Code)

Max Activating Token Index: 948

Text #14

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1413063 (Python Code)

Max Activating Token Index: 761

Text #15

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.0928. Min Act: -0.0000

Data Index: 1657047 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1616406 (Python Code)

Max Activating Token Index: 897

Text #17

Max Range: 1.6837. Min Range: -1.6837

Max Act: 1.0819. Min Act: -0.0000

Data Index: 1369484 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 1.6837. Min Range: -1.6837

Max Act: 0.9809. Min Act: -0.0000

Data Index: 605907 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.6837. Min Range: -1.6837

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1630173 (Python Code)

Max Activating Token Index: 107