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

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

Neuron 2351 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: 0.1114. Min Range: -0.1114

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1634945 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1500149 (Python Code)

Max Activating Token Index: 331

Text #2

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1505588 (Python Code)

Max Activating Token Index: 173

Text #3

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1605774 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1572800 (Python Code)

Max Activating Token Index: 221

Text #5

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1109. Min Act: -0.0003

Data Index: 1383581 (Python Code)

Max Activating Token Index: 927

Text #6

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1511981 (Python Code)

Max Activating Token Index: 603

Text #7

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0917. Min Act: -0.0003

Data Index: 131474 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1452183 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0925. Min Act: -0.0003

Data Index: 1442260 (Python Code)

Max Activating Token Index: 424

Text #10

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0874. Min Act: -0.0003

Data Index: 100681 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1491338 (Python Code)

Max Activating Token Index: 378

Text #12

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0868. Min Act: -0.0003

Data Index: 1648668 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1507284 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0854. Min Act: -0.0003

Data Index: 707524 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0803. Min Act: -0.0003

Data Index: 1193523 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1611543 (Python Code)

Max Activating Token Index: 118

Text #17

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0827. Min Act: -0.0003

Data Index: 1565360 (Python Code)

Max Activating Token Index: 128

Text #18

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0792. Min Act: -0.0003

Data Index: 789306 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0838. Min Act: -0.0002

Data Index: 46078 (C4 (Web Text))

Max Activating Token Index: 50