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

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

Neuron 3607 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0641. Min Range: -1.0641

Max Act: 1.0641. Min Act: -0.0000

Data Index: 75895 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.0641. Min Range: -1.0641

Max Act: 1.0359. Min Act: -0.0000

Data Index: 729844 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9586. Min Act: -0.0000

Data Index: 728769 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9666. Min Act: -0.0000

Data Index: 419386 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1411653 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1321788 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9473. Min Act: -0.0000

Data Index: 618797 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8899. Min Act: -0.0000

Data Index: 635937 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1314977 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 1.0641. Min Range: -1.0641

Max Act: 1.0105. Min Act: -0.0000

Data Index: 933017 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1029957 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1347018 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9151. Min Act: -0.0000

Data Index: 868580 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9039. Min Act: -0.0000

Data Index: 673207 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1436306 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9051. Min Act: -0.0000

Data Index: 653536 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8943. Min Act: -0.0000

Data Index: 123082 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1143148 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1992 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8383. Min Act: -0.0000

Data Index: 429704 (C4 (Web Text))

Max Activating Token Index: 235