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

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

Neuron 4259 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.2056. Min Act: -0.0000

Data Index: 659491 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1098825 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.1218. Min Act: -0.0000

Data Index: 698070 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.1239. Min Act: -0.0000

Data Index: 1325774 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.1257. Min Act: -0.0000

Data Index: 416870 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0441. Min Act: -0.0000

Data Index: 451824 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1228708 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0828. Min Act: -0.0000

Data Index: 670347 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1255475 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1158781 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1564703 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0516. Min Act: -0.0000

Data Index: 864750 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1212023 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0847. Min Act: -0.0000

Data Index: 925677 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1016108 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1287682 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0110. Min Act: -0.0000

Data Index: 804661 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0026. Min Act: -0.0000

Data Index: 845958 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.9694. Min Act: -0.0000

Data Index: 365691 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1167806 (C4 (Web Text))

Max Activating Token Index: 433