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

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

Neuron 3964 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: 1.5934. Min Range: -1.5934

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1220337 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1050873 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5934. Min Act: -0.0000

Data Index: 1272653 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1020065 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.1484. Min Act: -0.0000

Data Index: 753117 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.2060. Min Act: -0.0000

Data Index: 735737 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 1.5934. Min Range: -1.5934

Max Act: 0.9931. Min Act: -0.0000

Data Index: 801579 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1247261 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.0643. Min Act: -0.0000

Data Index: 888910 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.0833. Min Act: -0.0000

Data Index: 44206 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.0671. Min Act: -0.0000

Data Index: 422899 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 1.5934. Min Range: -1.5934

Max Act: 0.9253. Min Act: -0.0000

Data Index: 923984 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.0348. Min Act: -0.0000

Data Index: 8137 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 1.5934. Min Range: -1.5934

Max Act: 0.9347. Min Act: -0.0000

Data Index: 95699 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.5934. Min Range: -1.5934

Max Act: 0.8625. Min Act: -0.0000

Data Index: 260863 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 1.5934. Min Range: -1.5934

Max Act: 0.8626. Min Act: -0.0000

Data Index: 240410 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.5934. Min Range: -1.5934

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1322549 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.5934. Min Range: -1.5934

Max Act: 0.8840. Min Act: -0.0000

Data Index: 913841 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 1.5934. Min Range: -1.5934

Max Act: 0.8262. Min Act: -0.0000

Data Index: 781950 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.5934. Min Range: -1.5934

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1449478 (Python Code)

Max Activating Token Index: 956