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

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

Neuron 2927 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1697. Min Act: -0.0000

Data Index: 1365450 (Python Code)

Max Activating Token Index: 783

Text #1

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1574204 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1638164 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1438442 (Python Code)

Max Activating Token Index: 217

Text #4

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1499458 (Python Code)

Max Activating Token Index: 942

Text #5

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1600397 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1620490 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1449518 (Python Code)

Max Activating Token Index: 638

Text #8

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1556629 (Python Code)

Max Activating Token Index: 987

Text #9

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1550510 (Python Code)

Max Activating Token Index: 1005

Text #10

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1427661 (Python Code)

Max Activating Token Index: 910

Text #11

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1577990 (Python Code)

Max Activating Token Index: 1015

Text #12

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1445581 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1470854 (Python Code)

Max Activating Token Index: 643

Text #14

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1449041 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1449839 (Python Code)

Max Activating Token Index: 1022

Text #16

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1509962 (Python Code)

Max Activating Token Index: 881

Text #17

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1646086 (Python Code)

Max Activating Token Index: 459

Text #18

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1369915 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1441590 (Python Code)

Max Activating Token Index: 905