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

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

Neuron 3213 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0002

Data Index: 498671 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1108843 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0069. Min Act: -0.0002

Data Index: 728681 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1018879 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1100564 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0002

Data Index: 977384 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0002

Data Index: 394749 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0002

Data Index: 260334 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 316983 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 513761 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 947158 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 720062 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0002

Data Index: 804579 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 670665 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1628446 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0002

Data Index: 906695 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0002

Data Index: 517712 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0002

Data Index: 960278 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0058. Min Act: -0.0002

Data Index: 210089 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0058. Min Act: -0.0002

Data Index: 664019 (C4 (Web Text))

Max Activating Token Index: 325