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

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

Neuron 3309 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: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0002

Data Index: 721116 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0002

Data Index: 540152 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0002

Data Index: 763786 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0002

Data Index: 125090 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0002

Data Index: 680431 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0002

Data Index: 487203 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0002

Data Index: 7344 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0002

Data Index: 568084 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0002

Data Index: 809417 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1107732 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0002

Data Index: 331535 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0002

Data Index: 1046503 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0001

Data Index: 1630666 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0002

Data Index: 1206646 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0002

Data Index: 432395 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0002

Data Index: 189669 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0002

Data Index: 641727 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0002

Data Index: 668516 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0002

Data Index: 896244 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0002

Data Index: 303429 (C4 (Web Text))

Max Activating Token Index: 295