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

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

Neuron 5890 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1581. Min Range: -2.1581

Max Act: 2.0338. Min Act: -0.0000

Data Index: 1170119 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.6724. Min Act: -0.0000

Data Index: 630043 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.9452. Min Act: -0.0000

Data Index: 1180437 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 2.1581. Min Range: -2.1581

Max Act: 2.1581. Min Act: -0.0000

Data Index: 33234 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.8679. Min Act: -0.0000

Data Index: 708224 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.5500. Min Act: -0.0000

Data Index: 656148 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.5889. Min Act: -0.0000

Data Index: 279633 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.9343. Min Act: -0.0000

Data Index: 1329895 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.9815. Min Act: -0.0000

Data Index: 242992 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.8563. Min Act: -0.0000

Data Index: 1033424 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.7577. Min Act: -0.0000

Data Index: 1620201 (Python Code)

Max Activating Token Index: 985

Text #11

Max Range: 2.1581. Min Range: -2.1581

Max Act: 2.0638. Min Act: -0.0000

Data Index: 672272 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.6858. Min Act: -0.0000

Data Index: 1225253 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.7563. Min Act: -0.0000

Data Index: 578368 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.7021. Min Act: -0.0000

Data Index: 263206 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.8482. Min Act: -0.0000

Data Index: 1173353 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.7818. Min Act: -0.0000

Data Index: 1029805 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.7908. Min Act: -0.0000

Data Index: 764547 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.6714. Min Act: -0.0000

Data Index: 236255 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 2.1581. Min Range: -2.1581

Max Act: 1.7025. Min Act: -0.0000

Data Index: 374806 (C4 (Web Text))

Max Activating Token Index: 756