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

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

Neuron 5996 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.8079. Min Act: -0.0000

Data Index: 1465542 (Python Code)

Max Activating Token Index: 350

Text #1

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1472661 (Python Code)

Max Activating Token Index: 859

Text #2

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.6446. Min Act: -0.0000

Data Index: 1493710 (Python Code)

Max Activating Token Index: 391

Text #3

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.5077. Min Act: 0.0000

Data Index: 1374109 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.5949. Min Act: -0.0000

Data Index: 1538441 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.5729. Min Act: 0.0000

Data Index: 1422235 (Python Code)

Max Activating Token Index: 790

Text #6

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.5570. Min Act: 0.0000

Data Index: 1446385 (Python Code)

Max Activating Token Index: 360

Text #7

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.6284. Min Act: -0.0000

Data Index: 1504379 (Python Code)

Max Activating Token Index: 987

Text #8

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4942. Min Act: -0.0000

Data Index: 1422969 (Python Code)

Max Activating Token Index: 531

Text #9

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.5592. Min Act: 0.0000

Data Index: 1413910 (Python Code)

Max Activating Token Index: 877

Text #10

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4881. Min Act: 0.0000

Data Index: 1479611 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4930. Min Act: -0.0000

Data Index: 1519486 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4643. Min Act: 0.0000

Data Index: 1571441 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4864. Min Act: -0.0000

Data Index: 1544752 (Python Code)

Max Activating Token Index: 682

Text #14

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1469714 (Python Code)

Max Activating Token Index: 485

Text #15

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4581. Min Act: -0.0000

Data Index: 1584189 (Python Code)

Max Activating Token Index: 804

Text #16

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.5523. Min Act: -0.0000

Data Index: 1630680 (Python Code)

Max Activating Token Index: 540

Text #17

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4293. Min Act: -0.0000

Data Index: 1493319 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3567. Min Act: 0.0000

Data Index: 1616342 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1527616 (Python Code)

Max Activating Token Index: 968