Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2530 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2903. Min Act: -0.0002

Data Index: 1647042 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1363497 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1363148 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0003

Data Index: 1363840 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1361771 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0003

Data Index: 1367528 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1363913 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1362470 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1362256 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0003

Data Index: 1365501 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0003

Data Index: 1361276 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1363881 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1360519 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0003

Data Index: 1360709 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1363137 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1365349 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1363939 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0003

Data Index: 1364491 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0003

Data Index: 1361118 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2853. Min Act: -0.0003

Data Index: 1363531 (Python Code)

Max Activating Token Index: 1