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

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

Neuron 3335 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: 569419 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1270839 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1186207 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0092. Min Act: -0.0002

Data Index: 45153 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1159253 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1071110 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1208123 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0091. Min Act: -0.0002

Data Index: 603552 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1077708 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0088. Min Act: -0.0002

Data Index: 360810 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 82597 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 38452 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 16532 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 339876 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 225192 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 13084 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 79830 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 198498 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 200506 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0002

Data Index: 176690 (C4 (Web Text))

Max Activating Token Index: 1