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

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

Neuron 4291 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8273. Min Range: -2.8273

Max Act: 2.8273. Min Act: -0.0000

Data Index: 1436413 (Python Code)

Max Activating Token Index: 998

Text #1

Max Range: 2.8273. Min Range: -2.8273

Max Act: 2.2493. Min Act: -0.0000

Data Index: 1611929 (Python Code)

Max Activating Token Index: 890

Text #2

Max Range: 2.8273. Min Range: -2.8273

Max Act: 2.0257. Min Act: -0.0000

Data Index: 1426776 (Python Code)

Max Activating Token Index: 1020

Text #3

Max Range: 2.8273. Min Range: -2.8273

Max Act: 2.0009. Min Act: -0.0000

Data Index: 1567384 (Python Code)

Max Activating Token Index: 981

Text #4

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1053738 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.8714. Min Act: -0.0000

Data Index: 1492755 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.8166. Min Act: -0.0000

Data Index: 1606908 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.8125. Min Act: -0.0000

Data Index: 1582853 (Python Code)

Max Activating Token Index: 649

Text #8

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.5209. Min Act: -0.0000

Data Index: 82188 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.8155. Min Act: -0.0000

Data Index: 1440307 (Python Code)

Max Activating Token Index: 544

Text #10

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.6869. Min Act: -0.0000

Data Index: 1433764 (Python Code)

Max Activating Token Index: 878

Text #11

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.6653. Min Act: -0.0000

Data Index: 1385488 (Python Code)

Max Activating Token Index: 675

Text #12

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.6677. Min Act: -0.0000

Data Index: 1556124 (Python Code)

Max Activating Token Index: 518

Text #13

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.6496. Min Act: -0.0000

Data Index: 1541199 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1523557 (Python Code)

Max Activating Token Index: 410

Text #15

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.7271. Min Act: -0.0000

Data Index: 1531847 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.6462. Min Act: -0.0000

Data Index: 1388866 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.7087. Min Act: -0.0000

Data Index: 1624218 (Python Code)

Max Activating Token Index: 642

Text #18

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.9086. Min Act: -0.0000

Data Index: 1033918 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 2.8273. Min Range: -2.8273

Max Act: 1.5258. Min Act: -0.0000

Data Index: 1465528 (Python Code)

Max Activating Token Index: 840