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

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

Neuron 3201 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.6911. Min Act: -0.0001

Data Index: 682665 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.6589. Min Act: -0.0001

Data Index: 1603719 (Python Code)

Max Activating Token Index: 981

Text #2

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4226. Min Act: -0.0000

Data Index: 1471246 (Python Code)

Max Activating Token Index: 857

Text #3

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4267. Min Act: -0.0000

Data Index: 769497 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5398. Min Act: -0.0001

Data Index: 1255503 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3832. Min Act: -0.0001

Data Index: 1516340 (Python Code)

Max Activating Token Index: 791

Text #6

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5012. Min Act: -0.0001

Data Index: 17995 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5873. Min Act: -0.0001

Data Index: 1558529 (Python Code)

Max Activating Token Index: 989

Text #8

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4683. Min Act: -0.0000

Data Index: 1469512 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4006. Min Act: -0.0001

Data Index: 509963 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3874. Min Act: -0.0001

Data Index: 1617432 (Python Code)

Max Activating Token Index: 567

Text #11

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4102. Min Act: -0.0001

Data Index: 67993 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4647. Min Act: -0.0000

Data Index: 165259 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4466. Min Act: -0.0001

Data Index: 233262 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4471. Min Act: -0.0001

Data Index: 1186103 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3410. Min Act: -0.0001

Data Index: 209466 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4704. Min Act: -0.0001

Data Index: 1421818 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3513. Min Act: -0.0001

Data Index: 1648318 (Python Code)

Max Activating Token Index: 523

Text #18

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3566. Min Act: -0.0001

Data Index: 1631322 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4830. Min Act: -0.0001

Data Index: 1429488 (Python Code)

Max Activating Token Index: 965