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

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

Neuron 4401 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: 0.0095. Min Range: -0.0095

Max Act: 0.0095. Min Act: -0.0002

Data Index: 880212 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1564534 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0095. Min Act: -0.0002

Data Index: 143205 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1002014 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 807135 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 659817 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1166066 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1014848 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 411726 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 495100 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1137593 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 865238 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 868728 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1191594 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0091. Min Act: -0.0002

Data Index: 890301 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0091. Min Act: -0.0002

Data Index: 207205 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1311476 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0090. Min Act: -0.0002

Data Index: 616025 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0090. Min Act: -0.0002

Data Index: 598647 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0089. Min Act: -0.0002

Data Index: 335306 (C4 (Web Text))

Max Activating Token Index: 1