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

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

Neuron 1195 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.5709. Min Act: -0.0000

Data Index: 1648924 (Python Code)

Max Activating Token Index: 67

Text #1

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.0966. Min Act: -0.0000

Data Index: 1605663 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.0355. Min Act: -0.0000

Data Index: 718513 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.1634. Min Act: -0.0000

Data Index: 1394405 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.1596. Min Act: -0.0000

Data Index: 532833 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.9157. Min Act: -0.0000

Data Index: 986174 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.9054. Min Act: -0.0000

Data Index: 1461577 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.8745. Min Act: -0.0000

Data Index: 358876 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.9782. Min Act: -0.0000

Data Index: 1577843 (Python Code)

Max Activating Token Index: 120

Text #9

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.8354. Min Act: -0.0000

Data Index: 749844 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.6972. Min Act: -0.0000

Data Index: 157455 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.7833. Min Act: -0.0001

Data Index: 1588715 (Python Code)

Max Activating Token Index: 55

Text #12

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.7897. Min Act: -0.0000

Data Index: 854913 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.7853. Min Act: -0.0000

Data Index: 1128486 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.9077. Min Act: -0.0000

Data Index: 1217231 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.7854. Min Act: -0.0000

Data Index: 975667 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.9048. Min Act: -0.0000

Data Index: 1410736 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.9045. Min Act: -0.0000

Data Index: 1432003 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.6081. Min Act: -0.0000

Data Index: 248606 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 3.5709. Min Range: -3.5709

Max Act: 2.8860. Min Act: -0.0000

Data Index: 477512 (C4 (Web Text))

Max Activating Token Index: 590