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

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

Neuron 200 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: 0.5680. Min Range: -0.5680

Max Act: 0.5680. Min Act: -0.0000

Data Index: 752069 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4516. Min Act: -0.0000

Data Index: 796033 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1020651 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1546645 (Python Code)

Max Activating Token Index: 911

Text #4

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1309204 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4413. Min Act: -0.0000

Data Index: 575746 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4484. Min Act: -0.0000

Data Index: 75629 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1176205 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1202188 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1590396 (Python Code)

Max Activating Token Index: 303

Text #10

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4108. Min Act: -0.0000

Data Index: 796946 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1571868 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.3935. Min Act: -0.0000

Data Index: 964377 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1270402 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4021. Min Act: -0.0000

Data Index: 953594 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1623785 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1373742 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1153214 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.3387. Min Act: -0.0000

Data Index: 135834 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1030846 (C4 (Web Text))

Max Activating Token Index: 316