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

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

Neuron 2445 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1413411 (Python Code)

Max Activating Token Index: 726

Text #1

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1420911 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0903. Min Act: -0.0000

Data Index: 1609846 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1570806 (Python Code)

Max Activating Token Index: 332

Text #4

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1387736 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0749. Min Act: -0.0000

Data Index: 1568226 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1364571 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1520810 (Python Code)

Max Activating Token Index: 836

Text #8

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1570526 (Python Code)

Max Activating Token Index: 176

Text #9

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1623258 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9654. Min Act: -0.0000

Data Index: 1439012 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1594496 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1602208 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1524767 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1530772 (Python Code)

Max Activating Token Index: 613

Text #15

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1446740 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1526546 (Python Code)

Max Activating Token Index: 197

Text #17

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1585766 (Python Code)

Max Activating Token Index: 502

Text #18

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1423142 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1379371 (Python Code)

Max Activating Token Index: 412