Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 649 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0102. Min Act: -0.0006

Data Index: 114566 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1610703 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1436142 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1543468 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0083. Min Act: -0.0006

Data Index: 84371 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0080. Min Act: -0.0006

Data Index: 208382 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1587407 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1370916 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0084. Min Act: -0.0006

Data Index: 63495 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0077. Min Act: -0.0006

Data Index: 991843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1455373 (Python Code)

Max Activating Token Index: 539

Text #11

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0077. Min Act: -0.0006

Data Index: 185986 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0076. Min Act: -0.0006

Data Index: 654511 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0076. Min Act: -0.0006

Data Index: 630574 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1459245 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1570205 (Python Code)

Max Activating Token Index: 881

Text #16

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1590077 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1405903 (Python Code)

Max Activating Token Index: 850

Text #18

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0075. Min Act: -0.0005

Data Index: 292414 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0074. Min Act: -0.0006

Data Index: 95777 (C4 (Web Text))

Max Activating Token Index: 1023