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

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

Neuron 2429 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1070. Min Act: -0.0002

Data Index: 742048 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0919. Min Act: -0.0002

Data Index: 26436 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1246408 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0861. Min Act: -0.0002

Data Index: 166891 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0743. Min Act: -0.0002

Data Index: 288759 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1385241 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0826. Min Act: -0.0002

Data Index: 815506 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0804. Min Act: -0.0002

Data Index: 52141 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1110400 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1644111 (Python Code)

Max Activating Token Index: 348

Text #10

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0784. Min Act: -0.0002

Data Index: 18688 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1510061 (Python Code)

Max Activating Token Index: 743

Text #12

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1512885 (Python Code)

Max Activating Token Index: 438

Text #13

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1483935 (Python Code)

Max Activating Token Index: 865

Text #14

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1414893 (Python Code)

Max Activating Token Index: 798

Text #15

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0715. Min Act: -0.0002

Data Index: 988245 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0768. Min Act: -0.0002

Data Index: 887126 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1398920 (Python Code)

Max Activating Token Index: 120

Text #18

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0754. Min Act: -0.0002

Data Index: 921627 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1354758 (C4 (Web Text))

Max Activating Token Index: 845