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

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

Neuron 556 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: 1.2648. Min Range: -1.2648

Max Act: 1.2648. Min Act: 0.0000

Data Index: 1436799 (Python Code)

Max Activating Token Index: 1005

Text #1

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.1693. Min Act: -0.0000

Data Index: 463658 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.0897. Min Act: -0.0000

Data Index: 60083 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.1936. Min Act: -0.0000

Data Index: 992979 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.2018. Min Act: -0.0000

Data Index: 325894 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.1137. Min Act: -0.0000

Data Index: 762601 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.1736. Min Act: -0.0000

Data Index: 1575109 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1474126 (Python Code)

Max Activating Token Index: 346

Text #8

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.1074. Min Act: -0.0000

Data Index: 1488082 (Python Code)

Max Activating Token Index: 868

Text #9

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.0459. Min Act: -0.0000

Data Index: 132039 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1427968 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1632890 (Python Code)

Max Activating Token Index: 559

Text #12

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1473982 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1462060 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8457. Min Act: -0.0000

Data Index: 37365 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8244. Min Act: -0.0000

Data Index: 434250 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1418155 (Python Code)

Max Activating Token Index: 199

Text #17

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1374455 (Python Code)

Max Activating Token Index: 388

Text #18

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.5925. Min Act: -0.0000

Data Index: 246298 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1575095 (Python Code)

Max Activating Token Index: 1019