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

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

Neuron 2383 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: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0002

Data Index: 659671 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0002

Data Index: 590392 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0002

Data Index: 526812 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1227738 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0002

Data Index: 851145 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1171712 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0002

Data Index: 247376 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0002

Data Index: 259829 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1566032 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1307695 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0002

Data Index: 611311 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0002

Data Index: 646287 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0002

Data Index: 798821 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0002

Data Index: 492468 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0002

Data Index: 715670 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1511985 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0002

Data Index: 283475 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0002

Data Index: 119584 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1126813 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0002

Data Index: 516914 (C4 (Web Text))

Max Activating Token Index: 477